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

Very rich beyond annotations: franquia per credential, 30-day/pilot window, repetition not consuming another unit, no payment, no premium unlock, and required auth headers for reads and GET /geracao. This discloses the billing/authorization side effects that justify readOnlyHint=false.

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 core purpose is front-loaded, but the description sprawls across billing, quota windows, premium headers, and pilot budget in an unstructured way. Several sentences earn their place, but the overall flow is dense and could be tightened.

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 tool with no output schema, it covers limits, cost, credentials, and the premium hand-off. It does not explain the synchronous return vs the separate avaliacao_basico_resultado tool, leaving a small gap in how results are retrieved.

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 coverage is 100% and both parameters (id, agent_pass) are documented in the schema, so the description adds little parameter-specific syntax. Baseline 3 applies.

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?

States a clear verb+resource with scope: native/OCR text extraction from PDFs up to 50 pages/32 MiB, without review or structured tables. This distinguishes it from the premium sibling variants, though it never names them explicitly.

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?

Gives concrete usage context: 100 documents per agent, no charge, no auto-renewal, and it points to the premium path (save evaluation.access_code and send X-Editalmd-Avaliacao). It does not explicitly say 'use avaliacao_premium instead when you need tables/premium content', but the limitations imply it.

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