write_coach_request

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

Beyond the annotations (destructive/openWorld/not-readOnly), it discloses cost ('spends the instance's provider budget'), concurrency ('one job per call, one at a time'), blocking behavior with the waitSec timeout and the ~1-minute client limit, the fallback path, and a prompt-injection warning that answer text is data not instructions. That is exactly the extra context annotations 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?

A single dense paragraph, front-loaded with the cost/concurrency caveat before the per-kind breakdown. Every sentence carries information, though the packing of three kind definitions plus timeout and injection caveats into one block is heavy.

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?

With no output schema, the description covers the return path adequately: the answer arrives after waiting up to waitSec, or must be fetched via read_coach, and its text is untrusted data. For a 7-param, nested-object mutation tool this is complete enough to call correctly.

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 only 14%, so the description must compensate. It explains the semantics of kind (all three enum values), refine, note, workoutId (with default = latest) and waitSec (default 40), which is strong; only lang and the nested intake fields are left to the schema, keeping it short of a 5.

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+resource ('Ask the AI Coach') and then enumerates the three distinct operations (plan/review/debrief) with what each does, including the refine-vs-intake split within 'plan'. This lets an agent distinguish it from read_coach and the admin_coach_* siblings without opening the schema.

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?

Gives per-kind routing guidance (plan for new/refine, review for training-since-last, debrief for a single workout) and names the alternative for the async case ('otherwise check read_coach later'). It does not state explicit when-not-to-use conditions, so it falls just short of a 5.

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