Write persona into your tools

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations (destructiveHint=false, idempotentHint=true) are supplemented by the description stating 'Writes only inside a managed block; never clobbers the user's own content.' This adds critical safety context beyond the structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two brief paragraphs: the first states purpose and a key safety feature, the second lists parameters and return. No wasted words, information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description mentions 'Returns: per-target outcomes,' which is adequate. It covers target selection, safety, and default behavior. Missing explicit usage guidance versus siblings, but overall complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds value by explaining default behavior for targets and the effect of force. It does not rely on the schema alone and provides meaningful context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it writes the user's persona into native instruction files of AI tools, specifying the key resources (CLAUDE.md, Cursor rules, etc.) and the action. It distinguishes itself from sibling tools like mindmap_persona which manage persona internally.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains default behavior (global Claude config + detected project tools) and optional parameters. However, it does not explicitly state when to use this vs. alternatives like mindmap_persona_set, leaving some ambiguity about context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.