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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds valuable context beyond annotations: it clarifies the temporal state (opinions pending EC decision), explains the committee scope (CHMP vs CVMP), and lists the returned fields. This is useful but doesn't cover every behavior (e.g., sorting or pagination details), which is acceptable given the annotations.

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?

The description is three sentences long, with the core purpose front-loaded. It efficiently conveys the resource, scope, returned fields, and representative queries. No filler or repetition; every sentence adds value.

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 tool with 5 optional parameters and no output schema, the description adequately explains what the tool returns and gives usage examples. The annotations cover safety and the schema covers parameter semantics. Minor gaps like pagination behavior or sorting are not essential for correct invocation. The description is complete enough for an agent to use the tool effectively.

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 description coverage is 100%, with each parameter (limit, since, category, opinion_status, include_decided) already having a clear description. The description does not add parameter-specific details beyond the schema, but it does reinforce the meaning of opinion_status through example queries. Baseline of 3 is appropriate since the schema carries the semantic load.

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 clearly states a specific verb-resource pair: returns medicines recommended for or against EU approval by EMA committees, specifically those awaiting EC decision. It also lists the returned fields (brand name, active substance, applicant, opinion status, date) and provides example questions that distinguish it from related tools like ema_recent_approvals.

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?

The description provides concrete example questions that indicate when to use this tool (e.g., 'which new medicines did the CHMP recommend for approval'). It doesn't explicitly name alternative tools or exclusion conditions, but the context and the emphasis on 'still awaiting the European Commission decision' clearly differentiates it from approval-status tools. Could be improved by explicitly stating when NOT to use it.

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