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

Annotations already declare readOnlyHint=true, openWorldHint=false, idempotentHint=true, destructiveHint=false, and the description complements this by explaining the data source (official Brazilian sources), the privacy context (no sensitive data, LGPD compliance), the payment model (pay-per-query with prepaid credit), and the responsibility split (client is data controller). This goes well beyond the annotations, detailing what the tool does not access (sensitive data) and the legal framework.

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, information-dense paragraph. It front-loads the core purpose and then covers key behavioral aspects compactly. It's longer than a simple sentence but covers a lot of ground efficiently. Could arguably be split into structured bullet points for readability, but the flow is logical.

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 tool with no output schema and 5 parameters, the description does a good job covering the essentials: what it does, where data comes from, data privacy, and commercial model. The main gap is in parameter semantics and the fact that it doesn't describe expected response format, though with no output schema present, the tool's return values are left to the agent's imagination. The description is reasonably complete for an external consultation tool.

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 and no parameter descriptions in the description, the tool relies entirely on the input schema property names (login, senha, mes, codigo_cliente, codigo_instalacao). The description adds no parameter-level semantics beyond what's in the schema, and the Portuguese terms (like 'mes' for month) might require locale understanding. The description doesn't explain the meaning or format of these parameters, especially codigo_cliente vs codigo_instalacao.

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 says 'Light: Download + OCR, consulta em fonte oficial' – it clearly identifies this as a download and OCR consultation tool with official sources, using a specific verb+resource structure. It distinguishes itself from siblings by explaining it's a data consultation tool but doesn't explicitly name a sibling alternative.

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 explains when to use it ('consulta em fonte oficial', 'mesma disponível ao cidadão'), implies the use case of querying official Brazilian sources, and clarifies that it doesn't require platform credentials. It offers implicit context for when to use (for official data queries) but does not explicitly state when not to use it or name alternatives.

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