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

Annotations already establish readOnly/idempotent behavior, and the description adds valuable semantics beyond them: it discloses that non-ICD-10 input returns is_csap:null with a proper error rather than false, and that notation variants like J18.1 and J181 produce the same result. This prevents serious misinterpretation.

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?

Four sentences, front-loaded with the core classification behavior, followed by notation handling, invalid-input semantics, and scope exclusion. Every sentence carries useful information and there is no filler.

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?

The tool has an output schema, so return shape is already covered. The description compensates for the remaining usage risks: invalid inputs, notation equivalence, and ICD-9 exclusion. Nothing needed for correct invocation appears to be missing.

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 documents cid_codes fully with examples, so the baseline is 3. The description adds actionable extra meaning by explaining that both OMS and SIH notations are accepted, which is not evident from the schema example alone.

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 ('Classifica') and resource ('códigos CID-10'), and clarifies the result: 'Retorna o grupo CSAP correspondente se aplicável'. This clearly distinguishes it from sibling listing/getting tools like list_csap_groups or get_icsap.

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 gives explicit exclusions: non-ICD-10 codes are not classified, and 6-digit ICD-9 SIH 1992–1997 codes are handled elsewhere ('não por esta ferramenta'). However, it does not name a specific sibling tool as the alternative, so the guidance is clear but not fully complete.

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