Update Persona

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

Goes well beyond the annotations: the whole text is replaced (matching destructiveHint), an empty string clears it, setup counts the step done while non-empty, and it returns {key, value}. The AI-key note about the app's own draft is exactly the kind of context structured fields cannot carry.

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?

Front-loaded with the verb+resource, then behavior, then the return shape. It is dense but nearly every clause adds operationally useful information; the Maestro AI-key aside is the one sentence that could be trimmed.

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?

Despite having no output schema, the description supplies the return shape ({key, value}) and covers clear-vs-set semantics and the setup side effect. Nothing an agent needs in order to call this one-parameter mutation correctly appears to be missing.

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 0% and the single 'text' parameter is undocumented in the schema, so the description carries the load. It does so by explaining that the parameter is the full persona text, is wholly replaced rather than merged, and that "" clears it — meaningful semantics the schema lacks.

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?

States a specific verb and resource ('Replace the user's persona') plus what the resource contains (direction, strengths, working style in the user's own words). It also distinguishes the persona from factual sources ('never as a source of facts'), separating it from KB-oriented siblings like kb_edit_profile or kb_capture.

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?

Explains downstream usage ('every writing prompt ... reads it for tone and emphasis') and rules out treating it as a fact store, and notes the in-app persona draft has no MCP tool, implying this is the only path. It does not give explicit when-not-to-call guidance or name a sibling alternative directly.

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