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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true. The description adds meaningful behavioral context beyond those: null fields are CLEARED while omitted fields are untouched, partial PAR-Q answers merge into previously stored flags, and the return value includes changed fields and ui_impact. It also explains that bone_joint_problem is deliberately excluded from clearance gating. This is substantial added context, though it doesn't cover every edge case.

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?

The description is dense but every sentence earns its place: it states the action, the timing, the null semantics, the injury routing, and the return-value usage. It is front-loaded with the core purpose and the most important usage rule. No filler or repetition of schema content.

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 complex tool with nested objects, an output schema, and 1 parameter, the description covers the critical operational details: when to call, how to handle nulls, how to handle injuries, and what to do with the response. The output schema exists, so the description needn't explain return values in detail, but it still tells the agent to confirm to the user that the answer was saved. Nothing essential is 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 description coverage is 100%, so the schema already documents the patch object and its fields. The description adds value by explaining the semantics of null vs omitted fields, the one-fact-per-call convention, and the special handling of injuries and PAR-Q flags. It doesn't enumerate every field, but the schema already does that, so the description's semantic additions are appropriate.

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 states a specific verb ('Persist facts the user confirmed') and a clear resource (the coaching profile), and enumerates the fact categories (goal, experience, schedule, equipment, injuries, preferences). It also distinguishes injury handling from the main tool by routing to add_injuries and resolve_injury_areas, which separates it from siblings.

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 gives explicit when-to-call guidance: 'Call as soon as a fact is confirmed — one fact per call is fine, don't batch or wait for the end of the conversation; works mid-workout too.' It also names alternatives for injuries (add_injuries, resolve_injury_areas), which is clear routing versus sibling tools.

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