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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds value beyond them by disclosing the output nature — questions with reasons, ordered by relevance — and a legal-advice disclaimer, which an agent needs to frame the result.

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 scope, then usage triggers, then output shape. Dense but every sentence carries information; the long first sentence is the only mild readability cost.

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?

No output schema, but the description explains what comes back (questions plus reasons) and the non-advice caveat, and the input enums are fully covered in the schema. Sufficient for an agent to call and interpret it, though slightly more on ordering behavior could help.

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%, with enum values and their meanings fully documented in the schema, so the baseline is 3. The description only implicitly links 'that tool and that data' to the ordering, adding marginal meaning beyond structured 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?

States a specific verb (lists checks) plus resource (UK GDPR checks before client/staff data goes into AI), and scopes it to UK firms with ordering by relevance. It is readily distinguishable from siblings like draft_ai_policy, which produces a document rather than a checklist.

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 rich, concrete triggers: an owner asking about ChatGPT, GDPR compliance of ChatGPT/Copilot, staff pasting customer details, or questions for an AI supplier. It lacks explicit exclusions or named alternatives (e.g. when to prefer draft_ai_policy), so it stops short of the top band.

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