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

With annotations declaring destructiveHint=false and idempotentHint=false, the description still adds real value: redirect validation, bounded transfer, integrity verification before storage, non-mutation of document body/revision, source URL and checksum not retained, and no server-side replay of failed requests. It avoids contradicting the annotations. It doesn't state the deployment size limit value or concrete failure/error surface, keeping it short of 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?

Front-loaded with the core action and the integrity constraint, then the linking recipe, then sibling routing — a sensible order. A few clauses (the 'ordinary string' phrasing, the non-retention note restated from the schema) come close to redundancy, but nothing is filler.

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 7-parameter, non-idempotent write tool with an output schema present, the description covers what gets mutated (nothing in the body), what is returned (attachment_uuid), what is discarded (source URL/checksum), and the follow-up needed to actually render the file. No gap an agent would trip over.

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 100%, so the baseline is 3; the description earns more by stressing that expected_sha256 must be independently supplied by the source service and never invented, and that expected_size_bytes must match exactly. filename and tenant_slug are left entirely to the schema, so it does not fully exploit the space.

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 specific verb (attach) and resource (exact original bytes from a public HTTPS URL to an existing document), and explicitly distinguishes itself from the two nearest siblings by naming them and their input sources. An agent can route between import_url, import, and begin_upload without opening a schema.

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 names the alternatives and the condition that selects each ('For a chat-host file object use kb_attachments_import; for local bytes use kb_attachments_begin_upload'). It also covers the retry case: a failed one-use source must be replaced with a fresh capability before a deliberate retry.

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