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

Beyond the annotations, the description discloses meaningful behavioral details: it returns at most 10 documents ordered by relevance, uses an empty list for no matches, works in Portuguese or English, ignores accents and case, and is backed by an in-memory cache of a public source. These details help an agent predict results accurately.

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 front-loaded with the core capability and then provides routing context, query guidance, and behavior in separate sections. It is somewhat dense and repeats the read-only/idempotent hints already present in annotations, but every paragraph earns its place by helping agents choose and use the tool.

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?

With one optional-free parameter, an output schema present, and clear return-shape details in the description, there is no missing information needed to invoke the tool correctly. The description even covers the no-match case and the follow-up `fetch` step, making it complete for an agent.

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?

The input schema already covers the single `query` parameter at 100%, so the baseline is 3. The description adds value by specifying Portuguese or English as accepted languages and clarifying that natural language or keywords are both valid, slightly extending what the schema says.

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 states a specific verb and resource: it searches the medical terminologies catalog and returns matching documents with an explicit shape and limit. It also distinguishes itself from the terminology data tools by clarifying it is a catalog index, not a data query, which prevents confusion with sibling `*_search` tools.

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 explicitly says when this tool is required — the OpenAI Deep Research contract requires `search` and `fetch` — and explicitly routes direct data questions to the terminology tools (`icd11_*`, `cid10_*`, etc.). It also tells the agent to pass returned ids to `fetch`, giving clear workflow guidance.

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