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

Annotations already declare readOnlyHint and destructiveHint, so the safety profile is covered. The description adds useful behavioral context: it's a presigned URL requiring a separate HTTP PUT, company-scoped, and returns a source_s3_uri for downstream use. It doesn't contradict annotations. A minor gap is not mentioning URL expiry or permissions, but the annotations lower the baseline.

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 efficient; it front-loads the core purpose and then packs workflow, kind distinctions, and next steps into two sentences. Slightly long but every clause adds value. Could be split for readability, but it's appropriately sized.

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 3 params, a nested object, and an enum, the description covers the essential workflow and scope, including next steps. It doesn't cover all enum variants or error cases, but the output schema exists and the main use cases are well documented. The mention of 'every document-import flow' gives a sense of the bigger picture.

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 low (33%: only companyId has description), but the description compensates by explaining the meaning of 'kind' values (SAFE, RSA, CAP_TABLE, WIRE_PROOF) and recommending mime_type=application/pdf. It omits the EIN_DOCUMENT and DOCUMENT enum values, but the described use cases cover the main flow. It also clarifies company scoping.

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 returns a presigned S3 PUT URL for uploading a company document, specifying the exact kinds (SAFE, RSA, CAP_TABLE, WIRE_PROOF). It distinguishes this tool from siblings by framing it as 'Step 1 of every document-import flow' and referencing the next steps.

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?

Explicitly explains when to use it: call with matching kind and mime_type=application/pdf, upload via HTTP PUT, then pass source_s3_uri to the next step. Provides named alternatives for each kind (ImportSAFE, ExtractRsaTermsOcr, ExtractCapTableOcr) and notes 'Company-scoped — no formation record needed,' making when-to-use very clear.

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