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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description still adds real behavioral detail beyond that: every read re-checks current publication, withdrawn bases return 404, and no cached files are served after withdrawal. It does not describe response size or streaming behavior, so it is not a 5.

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 download purpose and publication/404 rules are front-loaded and useful. But the middle 'Use base.embed_url in an iframe...' sentences describe embedding search and pagination limits that are tangential to downloading a DOCX file, adding length without helping the caller invoke this 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?

For a read-only download tool with no output schema, the definition covers the key facts an agent needs: published-only access, no account, 404 on private/withdrawn, no stale cache, and the untrusted-text warning. It is complete enough to call safely, with only the sibling-selection rule missing.

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% and both parameters (base_id, document_id) are documented in the schema as 64-character IDs. The description adds no additional parameter meaning, so the baseline 3 applies.

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 first sentence gives a specific verb and resource: 'Download the DOCX source linked by the OKF concept.' The word 'DOCX' implicitly separates it from the pdf_source, markdown, image and original siblings, but it never names them or states a selection rule, so an agent must infer the format-based routing.

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 states the access condition ('Published bases only. No account required.') and the failure mode for private/withdrawn bases (404), which is useful context. However, it never says when to choose this DOCX route over public_read_base_pdf_source, public_read_base_source or public_read_base_original, and the iframe paragraph describes embedding, not when to invoke this tool.

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