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

Annotations declare the safety profile (non-read-only, idempotent, non-destructive) already, so the description's job is to add context — and it does: message is a full replacement not a patch, prior versions are retained by the team, closed feedback is immutable, and the call is exempt from the daily quota. These are non-obvious behavioral traits that the annotations cannot convey.

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 core action and its contrast to send_feedback, then layered preconditions and quota note. Every sentence carries distinct information, though the paragraph is denser than strictly necessary for a 4-parameter tool.

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?

An output schema exists, so return values need not be described. With annotations covering the safety profile and the description covering replacement semantics, immutability of closed feedback, versioning, quota, and a user-consent instruction, nothing an agent needs to call this correctly 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 coverage is 100%, so the baseline is 3, but the description genuinely adds semantics the schema does not: 'message replaces the whole text, so send the complete updated wording, not just the change' clarifies replacement vs merge behavior, and 'kind and about change only if given' clarifies optional-update semantics. This goes beyond restating field names.

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 ('Change feedback this account already sent') and immediately distinguishes itself from siblings by naming where the id comes from (send_feedback or list_feedback). An agent can tell this apart from send_feedback and list_feedback without opening any 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?

Explicitly frames the choice against the alternative ('when the user wants to add to, correct, or refine it, instead of sending it again'), names the prerequisite id sources, states the 'Ask the user first' precondition, and gives an exclusion ('Closed feedback cannot be changed'). When-to-use, when-not-to-use, and alternatives are all present.

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