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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds valuable non-obvious behavior: a 5-minute server-side cache, how to bypass it, the underlying endpoint, and an LGPD/health-data sensitivity flag. It stops short of anything about error behavior or partial results, but that is a minor gap against rich added context.

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?

Two dense sentences with zero filler: fields returned first, then the cache rule, then the endpoint. Every clause carries information an agent can act on.

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 no output schema, the description usefully enumerates expected return fields, and it covers caching, sensitivity, and the endpoint. It is nearly complete for a read tool; only the id-vs-CPF precedence and the two boolean include flags are left to the schema.

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 80%, so patient_id, cpf, and fresh are already documented in the schema. The description only reinforces the id-or-CPF selector and adds timing context for fresh ('right after an edit'); it says nothing about include_photo_url or include_health_program beyond their existing schema text. Baseline 3 is appropriate.

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?

Specific verb and resource: retrieves exactly one patient, keyed by id or CPF, and enumerates the returned fields (name, birth date, contacts, address, insurance). This clearly separates it from feegow_list_patients and feegow_create_patient without the agent opening either 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?

Implies single-record retrieval via 'one patient by id or CPF' and gives a concrete conditional rule: set fresh=true right after an edit. It does not explicitly name feegow_list_patients as the alternative for bulk lookup, so the routing guidance is strong but not complete.

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