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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds substantial context: revocation blocks downloads even with an existing session or key, the initial grant requires the owner's session with origin and CSRF checks, org API keys stay within existing grants, and responses are private/no-store. These are meaningful auth and caching disclosures, though some read as generic access-policy boilerplate rather than DOCX-specific behavior.

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 first sentence is well front-loaded, but the remaining block is long and largely tangential to a single-file download: sentences about collection sharing granting future files, other owners' bases exposing published files, and sharing not publishing a resource do not help the agent invoke this tool. Much of the text reads as family-wide boilerplate that fails the 'every sentence earns its place' test.

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 read-only download tool with 100% schema coverage and full annotations, the description covers the important operational context: access is evaluated on every request, revocation takes effect immediately, session/CSRF requirements for the initial grant, and no-store responses. The only gap is that the returned payload format (a binary DOCX file rather than JSON) is never stated, and there is no output schema to compensate.

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 100%, so the schema already documents base_id, document_id and organization_id (including that organization_id must come from list_knowledge_teams and OKFIndex must be enabled). The description adds no parameter-level syntax or constraints beyond that, so the baseline of 3 is correct.

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?

First sentence gives a specific verb (Download) and resource (DOCX source) with a scoping qualifier (linked by the OKF concept), so the agent knows exactly what it retrieves. The team scoping is conveyed through the access-policy text (membership, product access, sharing), but the description never explicitly contrasts this with the sibling read_base_docx_source, so it falls short of a 5.

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 implies team context via 'Team access uses current account membership, product access and resource sharing', which tells the agent this is the team-authenticated variant. However, it never states when to use this over read_base_docx_source or public_read_base_docx_source, nor any prerequisites framed as usage conditions. Usage is only implied.

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