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

Annotations already declare idempotentHint=true, readOnlyHint=false, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context beyond that: the answer is 'immutable', it binds to the 'exact active publication and question', and retries should reuse the idempotency key. What it omits is the precondition on how to obtain a valid target.

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 tightly written sentences with zero filler; the core action is front-loaded and the retry rule follows immediately. Appropriately sized for the definition's scope.

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 9-parameter mutation with no output schema and 44% schema description coverage, two sentences leave gaps: the immutability story is stated but the dependency on get_run_calibration_review for a valid target and the correction-required-on-incorrect rule live only in the schema. Annotations carry the safety and idempotency burden, so the definition is functional but not 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 only 44% across 9 parameters. The description's phrase 'exact active publication and question' supplies semantic intent for expectedPublication and expectedQuestionStateHash, which the schema leaves undocumented, and reinforces idempotencyKey's retry role. It does not clarify correction, customerId scoping, or target sourcing beyond what the schema already states.

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 ('Record one immutable calibration answer') scoped to 'the exact active publication and question', which clearly separates it from structural siblings like record_review_decision and record_gate_result. Lacks an explicit named alternative, but the resource is unambiguous.

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?

Provides one concrete usage rule ('Reuse the same idempotencyKey when retrying a lost response'), which is useful retry guidance. However it says nothing about when to call this versus get_run_calibration_review or other record_* tools, so the when-to-use decision is only implied.

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