building-agent-tools
Guide for creating effective tools for AI agents. Use when building MCP tools, agent APIs, or any tool interface that agents will consume. Focuses on token efficiency, meaningful context, and proper namespacing.
What this skill does
# Building Tools for AI Agents ## Workflow 1. **Define Purpose** - Identify what agents need to accomplish with this tool - Determine if existing tools can be consolidated - Plan the tool's interface for agent consumption 2. **Design Interface** - Choose descriptive, namespaced tool names - Define parameters with clear types and descriptions - Design output format for maximum signal, minimum tokens 3. **Implement** - Build with token efficiency in mind - Add pagination, filtering, sensible defaults - Return semantic identifiers, not raw IDs 4. **Validate** - Test with real agent workflows - Check token consumption patterns - Verify error messages guide agents toward solutions ## Design Principles **Tool Consolidation** - More tools don't lead to better outcomes - Combine related operations into single tools - Example: `schedule_event` that checks availability AND creates event - Avoid simple CRUD-style tools that require multiple calls **Namespacing** - Prefix related tools with service name: `asana_projects_search`, `asana_users_search` - Group by domain to help agents distinguish functionality - Use consistent naming patterns across tool families **Meaningful Context** - Return high-signal information, not raw data dumps - Resolve cryptic UUIDs to human-readable identifiers - Include `response_format` parameter (concise/detailed) for flexibility - Surface relevant metadata agents need for next steps **Token Efficiency** - Implement pagination with sensible defaults - Add filtering parameters to reduce unnecessary data - Truncate large responses intelligently - Prefer structured output over verbose prose **Tool Descriptions** - Invest heavily in clear, explicit descriptions - Describe what the tool does, when to use it, and what it returns - Include parameter constraints and valid values - Small description improvements yield large performance gains ## Anti-Patterns - Creating many granular tools instead of consolidated operations - Returning raw IDs that agents can't interpret - Omitting pagination on potentially large result sets - Vague tool descriptions that leave agents guessing - Error messages that don't help agents recover - Requiring agents to make multiple calls for common workflows ## MCP-Specific Patterns **Tool Registration** - Use descriptive `name` and `description` in tool schema - Define `inputSchema` with JSON Schema for parameters - Mark required vs optional parameters explicitly **Response Format** - Return structured JSON for predictable parsing - Include success/error indicators - Provide actionable error messages
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.