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

The description discloses that the operation does not persist results, which is a key behavioral trait not covered by annotations. It also provides important details about vesting field preservation and notes that SAFE/preferred instruments carry no vesting, adding significant value beyond the sparse 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 three sentences, front-loaded with the core purpose. The second and third sentences provide crucial behavioral details and a direct instruction about vesting fields, each earning its place without unnecessary verbosity.

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's complexity (3 parameters, nested objects, output schema), the description adequately covers purpose, non-persistence, vesting handling, and downstream usage. It does not explain the complete parameter set or error behavior, but the output schema and patterns cover some of that. The description is reasonably complete for an extraction tool.

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 low (33%), with only companyId described. The description adds some meaning by mentioning 'uploaded cap table' (implied sourceS3Uri) and 'active company' (implied companyId), but it does not explain mimeType at all. Partial compensation for the low coverage, but not complete.

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 runs vision OCR on an uploaded cap table for the active company and returns extracted rows without persisting them. This specific verb+resource combination distinguishes it from sibling tools like formation_extract_cap_table (likely non-OCR) and formation_extract_rsa_terms_ocr (specific to RSA terms).

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?

It provides clear context: the tool is for extracting cap table data without persisting it, and explicitly instructs to pass vesting fields to RecordCapTableInvestment. However, it does not explicitly mention alternative tools or when not to use this tool, so it lacks explicit exclusions.

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