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

Annotations include destructiveHint: false and openWorldHint: false, but the description adds the context that it does OCR processing on a PDF and requires an active company. It does not disclose details about file size limits, whether the company must have a formation, or what happens on failure. With annotations covering safety, the description adds some behavioral context but not deeply.

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 at two sentences, front-loading the core action and key scope. It avoids redundancy with the tool name, and the additional note about company scope is valuable. No wasted words, but could include a bit more usage guidance without becoming verbose.

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?

Given the tool has an output schema (which handles return values) and nested objects, the description need not explain outputs. However, it does not specify which parameters are required besides companyId, nor does it clarify whether sourceS3Uri is mandatory for the OCR operation (it is not in required, but likely needed in practice). The description is adequate for basic invocation but lacks guidance on optional parameters that may be necessary for actual OCR.

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 33% (only companyId has a description: 'UUID value wrapper.'). The description does not elaborate on agentCode or sourceS3Uri, but the schema provides patterns (e.g., S3 URI pattern and agentCode format) that are self-explanatory. The description adds the company scope but does not add semantics for the optional parameters, so it slightly compensates but remains at baseline.

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 verb 'runs vision OCR' on a 'SAFE PDF' for a company, distinguishing it from non-OCR extraction by naming the OCR variant. However, it does not explicitly distinguish from the sibling 'formation_extract_cap_table_ocr' or 'formation_extract_rsa_terms_ocr', though the SAFE term is specific. It is clear but lacks a direct differentiation statement.

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 'no formation required' and 'requires an active company', giving some context on when to use it. It does not explicitly state when NOT to use it or point to alternatives like 'formation_extract_safe_terms' (non-OCR) or other OCR tools. The guidance is implied but not fully explicit about selecting this over siblings.

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