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

The annotations already declare this is a non-destructive, non-open-world mutation, and the description adds real context beyond them: the PCBEditor team reads every rating, and a low rating with a comment tells them what to fix. That explains the consequence of submitting. It does not address repeat behavior — with idempotentHint=false, an agent can't tell whether re-rating a design creates a second rating or replaces the first.

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 sentences, front-loaded with what is recorded, then the sourcing rule, then the consequence. Every sentence adds something: definition, constraint, motivation. No filler or repetition of schema details.

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 simple three-parameter write with full schema coverage, no output schema, and annotations covering safety, the description is nearly sufficient — it covers what to send and how to obtain it. The remaining gap is outcome feedback: not whether the tool returns a confirmation, but whether a rating can be changed after submission, which matters for a non-idempotent call.

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, and the description earns above that by explaining whose value each parameter carries: the rating must be the user's own and the comment must be 'in their words'. That is meaning the schema cannot convey and directly shapes how the agent fills both fields.

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?

The description opens with a specific verb+resource: 'Records the user's own rating of a board PCBEditor designed, from 1 (poor) to 5 (great)'. It names the scale and the optional comment, so an agent knows exactly what this tool does and what it is not (it is not a read, review, or edit of the board).

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?

It gives explicit operating guidance: 'Ask the user and pass their answer as they said it; never rate on their behalf' — a clear precondition and prohibition. What's missing is an explicit trigger condition (e.g. 'use when the user expresses an opinion about a design they worked on'), so the when-to-invoke moment is inferred from the purpose sentence rather than stated.

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