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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering safety and scope. The description adds 'simGIC pré-computado' and 'explicável: nº de fenótipos em comum', which tells the agent results derive from precomputed similarity, not live computation, and that explainability comes via shared-phenotype counts. This extra context is valuable but does not describe the return structure, which is already covered by the output schema.

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 a single, dense sentence that packs the main purpose and a sibling reference without waste. It front-loads the core information and uses a colon to add the explainability detail. This is concise and structurally sound.

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 2-parameter read-only tool with an output schema, the description covers the essential distinction from its semantic sibling and notes the precomputed, explainable nature. However, it omits any guidance on parameter semantics, which is critical for correct invocation since schema coverage is 0%. Overall it provides a good high-level picture but leaves the agent without enough detail on how to construct a valid request.

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 schema has 0% description coverage, so the burden falls on the description, yet it never mentions 'orphaCode' or 'limit'. The tool name and title imply an input disease is needed, but the exact parameter (Orpha code) is not articulated. An agent would have to infer the meaning from the schema's pattern '^\d+$', which is not self-evident. Thus the description fails to compensate for missing schema param docs.

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 specifies 'Doenças com perfil de fenótipos HPO semelhante' – a clear resource (diseases) and criterion (similar HPO phenotype profiles). It also names the sibling it complements, 'find_similar_diseases (semântico)', providing immediate differentiation. This distinguishes the tool from alternatives without needing to open the 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?

The phrase 'Complementa find_similar_diseases (semântico)' explicitly points to the alternative and positions this tool as a phenotype-based counterpart. It tells the agent this is for phenotype profile similarity, not semantic similarity. However, it doesn't address other potentially related tools like find_diseases_by_phenotypes, leaving some ambiguity in broader tool selection.

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