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

Annotations only declare openWorldHint=false and destructiveHint=false, so the description carries the burden of behavioral disclosure. It clearly states the tool is non-persisting ('WITHOUT persisting anything'), explains the empty-string/0/false convention, and warns never to fabricate values. It also describes the required upstream upload flow. It doesn't detail rate limits or failure modes, but the non-persistence and no-fabrication rules are valuable behavioral context beyond the 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 dense but well-organized: it front-loads the core action and output, then the non-persistence guarantee, then the flow, then the follow-up. Every sentence earns its place, though the long list of vesting fields makes it slightly heavy. It is appropriately sized for a complex OCR extraction tool.

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 (OCR extraction, nested companyId object, output schema, upstream upload dependency), the description covers the critical context: the required upload flow, the non-persistence behavior, the no-fabrication rule, and the follow-up persistence path. It doesn't explain agentCode or the exact output schema shape, but the output schema exists and the description names the key extracted fields. This is nearly complete for an agent to invoke it correctly.

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 only 33% (only companyId has a description, and it's just 'UUID value wrapper'). The description compensates by explaining that sourceS3Uri must be the URI returned by GetOcrUploadURL, and it lists the extracted terms that map to the tool's purpose. It doesn't explain agentCode, but the description's flow guidance adds meaning beyond the schema.

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 verb ('Runs vision OCR'), a specific resource (already-uploaded signed RSA PDF), and the exact output (founder/company names plus structured terms). It also explicitly says it does NOT persist anything, which distinguishes it from sibling tools like formation_extract_safe_terms_ocr and cap_table_import_rsa.

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 gives an explicit flow: first call GetOcrUploadURL with kind=RSA, upload the PDF, then call this tool with the returned source_s3_uri. It also names the follow-up tool (CreateCapTableAgreement) and tells the agent to preserve vesting fields. This is clear when-to-use guidance with a concrete alternative.

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