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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read operation. The description adds the specific data source (SINTEGRA) and the state (SP), which is useful context. However, it doesn't disclose any additional behavioral traits like rate limits, authentication requirements, or what happens if both CPF and CNPJ are provided. With annotations covering the safety profile, a 3 is appropriate.

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, concise sentence that conveys the core purpose. It's front-loaded with the key information (SINTEGRA, SP, CNPJ/CPF). No wasted words. However, it could be slightly more structured by mentioning the read-only nature, but that's already in annotations.

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 tool's simplicity (2 optional parameters, no output schema, no nested objects), the description is mostly complete. It covers the purpose and the input parameters. However, it doesn't mention what the output looks like (since there's no output schema), nor does it clarify whether both CPF and CNPJ can be used together or if one is preferred. For a simple query tool, this is adequate but not exhaustive.

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%, so the description must compensate. The description mentions 'por CNPJ ou CPF', which indicates that either parameter can be used, but it doesn't explain the format, validation rules, or whether both can be provided simultaneously. The schema only defines the parameters as strings with no additional constraints. The description adds minimal value beyond the schema, so a 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?

The description clearly states the tool's purpose: it retrieves ICMS registration status (SINTEGRA) for the state of SP, using CNPJ or CPF. It specifies the resource (SINTEGRA registration) and the scope (SP state), which distinguishes it from sibling tools like consultas_sintegra_rj and consultas_sintegra_suframa. However, it doesn't explicitly mention that it's a read-only query, but that's covered by annotations.

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 implies usage: it's for checking ICMS registration status in SP. It doesn't explicitly state when to use this tool versus alternatives, but the state-specific scope (SP) and the mention of CNPJ/CPF provide some context. No exclusions or alternatives are mentioned, but the sibling tools for other states (RJ, SUFRAMA) are implicitly differentiated by the state name in the description.

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