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

Annotations declare readOnlyHint=false and idempotentHint=false but say nothing about cost or lifespan; the description adds that calls consume credential-bound units, expire at the earlier of 30 days or pilot end, and depend on a global budget. It also clarifies duplicate documents don't re-consume quota. This is meaningful behavioral context beyond the annotations, though it omits whether the call is synchronous or produces a retrievable artifact.

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 text is dense and back-loaded with pilot rules, budget caveats, and premium header names (X-Editalmd-Avaliacao, X-Agent-Pass) that are irrelevant to selecting or invoking this basic tool. Those sentences do not earn their place and distract from the core page/size limits stated in sentence one.

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 quota-consuming, credential-gated text extraction it covers limits, quota, and expiry, which is substantive. However, it never explains how the extracted text is retrieved (the evaluation_basic_result sibling implies an async or separate fetch) and provides no output-contract hint, leaving a gap for a mutation-style call with no output schema.

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 fully described in the schema, including the caveat that agent_pass is not the User-Agent. The description adds no parameter-level detail beyond generic credential discussion, so the baseline of 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?

The description states a specific verb and resource: extracting basic native or OCR text from a PDF, bounded at 50 pages / 32 MiB, excluding review or structured tables. It partially differentiates from evaluation_premium ('does not open premium content'), though it never names the sibling that offers premium text. Clear enough for an agent to identify the operation.

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?

It conveys quota context (up to 100 documents per agent, duplicates don't consume a unit) which implies this is a metered operation, but it never states when to choose this over evaluation_premium or how the result surfaces (evaluation_basic_result is a sibling). The premium paragraph describes headers rather than routing conditions, so usage is only implied.

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