Imagens das páginas escaneadas de um PDF

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

Adds substantial context beyond the annotations: writes files to disk (consistent with readOnlyHint=false), operates without external programs, keeps only the largest image per page and drops small logos, and reports unsupported encodings (CCITT, JBIG2, JPEG 2000) in an 'avisos' field. These are concrete behavioral traits an agent could not derive from the schema or annotations.

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?

Purpose is front-loaded and every sentence carries information (format handling, page selection, warnings, no-OCR caveat). The parentheticals and semicolon-dense clauses make it slightly heavy to scan, but nothing is filler.

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 file-writing tool with no output schema, the description covers where files go (referenced in schema), what each file represents, and how conversion failures surface via 'avisos'. It is nearly complete, though it does not state the naming/return convention of the written files explicitly.

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 100%, so the parameters are already documented, and the description adds only the page-image selection semantics (largest image is usually the full page). The 'paginas' range syntax and 'destino' default are left entirely to the schema, so 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?

States a specific verb and resource in the first clause ('Grava em arquivos as imagens das páginas de um PDF'), then specifies the per-format behavior (JPEG as-is, others PNG). It is clearly distinguishable from siblings like documento_inventario and documento_texto, both of which it references or implicitly contrasts with.

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?

Explicitly routes the agent: 'Use nas páginas que documento_inventario marca sem texto', naming the sibling call that produces the precondition. It also clarifies an edge case of that precondition (the PJe signature stamp does not count as text) and states what the tool cannot do (no OCR), leaving little to inference.

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