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

Annotations already declare readOnlyHint=true / destructiveHint=false / openWorldHint=false, but the description adds the meaningful, non-obvious behavior: this mints a presigned URL plus a source_s3_uri handoff token, and it clarifies that the real write happens out-of-band via an HTTP PUT to S3 rather than through this tool. It does not mention URL expiry, content-size limits, or whether repeated calls invalidate prior URLs, which are relevant for an upload-token tool.

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?

Front-loaded with what it returns, then the flow, then the per-kind handoff — the information order matches how an agent needs it. The second sentence is a long run-on enumerating three branches, and the parenthetical '(kind=SAFE for a SAFE PDF...)' is slightly repetitive, but every clause carries actionable content.

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?

An output schema exists, so return values need not be explained, yet the description still usefully names upload_url and source_s3_uri. For a 3-parameter nested-schema tool in a document-import pipeline, the main remaining gap is coverage of half the enum kinds and the companyId wrapper shape.

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%, and the description only partially compensates: it explains the semantics of four kinds (SAFE, RSA, CAP_TABLE, WIRE_PROOF) and prescribes mime_type=application/pdf. Four enum values (EIN_DOCUMENT, DOCUMENT, FAST, STAMPED_CERTIFICATE) are never mentioned, and the description uses shorthand 'kind=SAFE' rather than the schema's literal 'FORMATION_UPLOAD_KIND_SAFE', which risks an invalid call. companyId is a nested UUID wrapper object and its description never explains that nesting.

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?

States a concrete verb and resource (returns a presigned S3 PUT URL for a company document upload) and immediately enumerates the four document kinds it serves, with the literal purpose of each. It separates itself cleanly from siblings like formation_get_formation_document_download_url by making clear this is an upload-side, company-scoped URL and not a download of an existing formation document.

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 positions itself as 'Step 1 of every document-import flow' and routes each kind to its correct next tool (ImportSAFE, ExtractRsaTermsOcr then CreateCapTableAgreement with type=RSA, ExtractCapTableOcr). It also states the upload mechanic ('upload the file bytes to the returned upload_url with an HTTP PUT') and that no formation record is needed, so the agent knows both when to call it and what to do after.

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