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

Annotations already disclose readOnlyHint=false and destructiveHint=false, so the agent knows this is a non-destructive write. The description adds the important behavioral rule that content must be verbatim and not inferred, which is genuinely beyond the annotations. However, it says nothing about what happens on a repeat call (overwrite vs. append), whether the answer is scoped per seat per check, or whether it is visible to the person being coached — meaningful gaps for a write tool.

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?

Three tight sentences, front-loaded with what to record, then the enum nuance, then the hard constraint. No filler, and each sentence changes how the agent would fill the arguments.

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 5-parameter mutation with no output schema and 80% schema coverage, the description covers the judgment-heavy part (what counts as a valid answer, no inference). The remaining gap is lifecycle behavior on re-submission and visibility of the recorded answer, which the annotations do not cover either.

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 80%, so the baseline is 3, and the description earns above that by giving real semantics for the response enum: 'partly' is a legitimate answer and usually the most useful one, not a rounding error to yes/no. The 'in their own words' phrasing also reinforces the note parameter's intent. check_key, check_version and seat_external_id are left to the schema, which already documents them adequately.

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 concrete verb and resource: recording a person's own yes/partly/no answer about their own seat, plus their verbatim words. This is clearly distinguishable from the adjacent coaching tools (my_coaching_questions fetches the question, set_coaching_disposition sets disposition) because the description frames it as capturing the person's own utterance. It stops short of naming a sibling explicitly, so a 4 rather than a 5.

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 an explicit when-not: 'Only ever call this with what they actually said; never infer an answer from tone or from what they said about something else,' which is a real call precondition, not a restatement. It also pre-empts a likely misuse ('do not round partly to yes or no'). It does not route to an alternative tool for the infer-a-disposition case, which keeps it at 4.

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