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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description goes beyond this by disclosing the payment model ('pague por consulta com crédito pré-pago'), the public nature of the data ('ACESSO PÚBLICO em bases e fontes oficiais'), and LGPD compliance. It does not explain error handling or exact response format, but the annotations cover the main safety profile.

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 three sentences long, each adding value: the purpose, the access/payment model, and a legal note. It is front-loaded with the core function and contains no irrelevant filler. Every phrase earns its place.

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 complex tool with 10 parameters, no output schema, and no parameter descriptions, the description covers the high-level purpose, cost, and data nature, but leaves gaps: it does not specify the output format (e.g., range of similarity scores), the behavior of the 'completo' parameter, or potential error scenarios. It is adequate for basic selection but not for full autonomous invocation.

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 description coverage is 0%, with 10 parameters and no descriptions in the schema. The description mentions 'CURP, nome, nascimento, endereço', which loosely maps to several parameters, but it does not explain the 'completo' boolean, required formatting (e.g., CURP structure), or the meaning of each field. This is insufficient compensation for the complete lack of schema-level documentation.

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 the tool's function: 'Compara os dados informados de uma pessoa no México (CURP, nome, nascimento, endereço) e retorna o grau de similaridade com o cadastro.' This specifies the verb (compares), the resource (person data in Mexico), and the output (similarity degree). It also distinguishes itself from the unrelated sibling tools (authenticate, connect, etc.) by being a data validation tool.

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?

Provides useful context: hosted by the platform, no credentials required, pay-per-query with prepaid credit, and it queries public-access information. This implies when to use it (for identity/similarity checks using public data) and highlights its paid nature. However, it does not explicitly state when not to use it or compare with alternative tools, though no comparable siblings exist.

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