feedback_send

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

Annotations only flag openWorldHint and non-read-only; the description supplies the operationally important traits: it is free, capped at 10 delivered reports/hour per account, and the correct response to a 429 is to wait rather than loop. It also carries the writing constraint around secrets.

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 purpose followed by rate-limit behavior and submission discipline. Every sentence carries a distinct instruction; nothing is redundant or padded.

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 side-effecting submit tool with 100% schema coverage and no output schema, the description covers everything an agent must know: what to report, what to include, what to avoid, how to react to throttling, and the need for user consent.

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 adds real semantic content: it tells the agent what belongs in `details` (the exact call, what came back, what was expected, ids like research_id) and forbids secrets/API keys. That goes beyond the schema's terse 'exact call, what came back' note.

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?

Opens with a specific verb (report) and enumerates the supported report kinds (bug, wrong/empty field, missing capability, question), scoping the tool to ProspectAPIs. No sibling tool overlaps with this function, so it is trivially distinguishable.

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?

Explicit when-to-use and when-not-to-retry rules: 'Send only when the user agrees', re-run the call to confirm a field is genuinely wrong before reporting, and 'a 429 means wait, do not retry in a loop'. This is about as actionable as usage guidance gets.

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