visual_evaluate_document

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

Without annotations, the description reveals key behaviors: it returns content blocks (text/images) and can run local OCR. It implies a read-only operation by using 'extract', but does not clarify if the document is modified or detail potential side effects.

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 concise, with two sentences that front-load the core purpose and key feature (inline images). No unnecessary details or repetition.

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 5 parameters and no output schema, the description provides a general overview but lacks detail on parameter defaults, supported file formats, and error handling. Sibling differentiation is not explicitly addressed, leaving some gaps for an AI agent.

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 0%, so the description must compensate. It hints at file_path (document), enable_ocr (optional OCR), page (page number), but does not describe max_pages or ocr_lang explicitly. This partial coverage leaves some parameters ambiguous.

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 clearly states the tool extracts visual content (charts, tables, diagrams) from PDFs/images and returns inline images for AI analysis. This distinguishes it from siblings like read_document (text extraction) and document_info (metadata).

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 mentions optional OCR usage but does not explicitly state when to use this tool over alternatives or any constraints (e.g., file size limits). Usage context is implied but not clearly delineated.

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