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

Annotations already convey readOnly, idempotent, and non-destructive behavior. The description adds that image input is OCR'd first and that the output is structured JSON, but it adds little beyond that; no rate limits, processing constraints, or empty-input behavior are disclosed. No contradiction with 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?

The description is very short and front-loaded with the core action: 'Multimodal extraction. Send an image, text, or both; define your schema; get structured JSON.' There is minor redundancy between 'Multimodal extraction' and 'Unified multimodal field extraction,' but the overall structure is efficient.

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?

The description covers the main workflow and output type, but with no output schema it leaves the precise JSON return shape vague. It also does not explain what happens when all optional parameters are null, which the schema permits. For a tool with rich annotations and only three optional parameters, this is a moderate gap.

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%, and the field_schema parameter includes an inline example. The tool description itself only mentions 'define your schema of fields,' adding little over the schema, so the baseline score of 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?

The description states a specific behavior: multimodal field extraction from images and/or text into user-defined structured JSON. 'Unified multimodal field extraction over images and text' clearly differentiates it from document-specific siblings like document_extract and document_tables, while the custom field-schema aspect distinguishes it from simpler OCR tools.

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 implies usage by instructing the agent to send image/text and define a schema, but it never explicitly says when to prefer this tool over alternatives or when not to use it. Given the overlapping sibling tools (document_extract, document_query, document_tables), explicit routing guidance is missing.

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