Read Document

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

Annotations already declare readOnlyHint and openWorldHint=false, so the description is not carrying the safety burden. It earns credit for disclosing behavior beyond the annotations: text is returned in chunks of ~15k characters and scanned PDF pages come back as images rather than text — both non-obvious traits an agent must plan around.

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?

Two short sentences, front-loaded with the core action and format scope, with the chunking/image caveats trailing. No filler and no repetition of the schema or 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?

For a two-parameter reader with no output schema, the description covers format coverage, chunked returns, and the image fallback for scanned pages. It does not say what happens when `part` exceeds the available number of parts or whether the ZIP listing is separate from extracted content, which are the only remaining gaps.

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%, so the schema already documents both id and part (baseline 3). The description adds meaning by explaining why `part` exists — content arrives in ~15k-character chunks — which tells the agent how to reason about chunk size, not just the field type.

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 specific verb ("Lê") and resource ("documento anexado") and enumerates the supported formats (PDF, Word, Excel, PowerPoint, HTML, texto, ZIP listing). That format list implicitly separates it from view_images and transcribe_audio, though no sibling is named 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?

Usage is only implied through the format list; there is no explicit "use this when / use X instead" guidance. The clause noting that scanned PDF pages arrive as images is a useful hint toward view_images, but it is not framed as a routing rule.

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