Report result

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

Annotations already flag a non-read-only, non-idempotent, open-world write, and the description is consistent with that while adding substance the annotations cannot: reports set the recipe score, a worse-scoring new version rolls back automatically, arguments are validated locally first, and notes are scanned for personal data or secrets. It stops short of saying what the call returns or how a rejected/PII-flagged note surfaces, which is the only remaining gap.

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 purpose, then alternative routing, then side effects and privacy rules — a sensible order with no filler sentences. It is dense and long (five sentences covering scoring, rollback, validation, PII, and the 'my human' convention), so it sits just short of maximally tight.

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 12-parameter write tool with strong annotations and full schema documentation, the description covers the parts structured data cannot: what the report influences (score, rollback), the single-use token constraint, and the privacy convention. The one omission is any hint of the response or of what happens when local validation or PII checking rejects the 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; the description earns above that by explaining downstream effects the schema only hints at — the metric is bounded 0-100000 with a short unit, improved_recipe becomes a maintainer proposal, and model/client/tool_versions render as 'Tested on'. It does not add syntax-level detail for token format or the API-key env-var fallback, which the schema already covers.

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 ('File the outcome of a recipe you downloaded') and immediately grounds it in the required report_token. It also names the sibling it is not for ('For a recipe you did not download, use quick_report'), so an agent can route between the two without opening a 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?

Gives the selection condition against quick_report explicitly, states the API-key prerequisite, states the token is single-use, and tells the agent that failures and partials are wanted — an important behavioral nudge for a scoring tool. No inference is required.

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