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

The description adds significant behavioral context beyond annotations: it specifies the return structure ({id}), bulk support via patient_ids/anamnesis_ids, the nature of overrides as a map with example keys, and default values for tipo and data. It also indicates that update overwrites existing fields. No contradictions with 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 well-structured with clear sections for actions, required/optional fields, and bulk support. It is concise but covers all necessary details. The line '[Flattened action: update]' is somewhat confusing but does not severely impact readability.

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?

Given the complexity (10 parameters, combined create/update actions, no output schema), the description covers key aspects: return value, parameter explanations, actions with required fields, and bulk. It could be more thorough on edge cases (e.g., what happens if both patient_id and anamnesis_id are provided), but overall it is quite complete.

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?

With 0% schema description coverage, the description compensates excellently. It explains the conditional requirements (patient_id vs anamnesis_id), the meaning of 'tipo' (1=completa, 2=simplificada), 'texto_livre' as HTML, 'data' as ISO, and 'overrides' as a map for extra fields with examples. This adds essential meaning beyond the raw schema.

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 it creates or updates an anamnesis in Dietbox and details the two actions. However, it lacks explicit differentiation from the sibling 'dietbox_anamnese_write_create' tool, which likely only creates. The verb+resource combination is specific and clear.

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 includes required fields per action (patient_id for create, anamnesis_id for update) and optional fields. However, it does not provide guidance on when to use this combined tool versus the separate create tool, nor any context about prerequisites or alternatives. The usage guidance is functional but incomplete.

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