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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: it explains that the server fetches the HTTPS URL rather than the model sending bytes, that size and type are verified before storage, that removal is destructive on the named attachment, and that a stable idempotency_key prevents duplicate uploads on retry. That idempotency/retry guidance is exactly the kind of behavior annotations cannot express.

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 add/remove dichotomy, then ordered by operational importance: fetch behavior, idempotency, read alternative, limits, allowed types. Dense and largely waste-free, though the trailing limits-and-types list reads as a compact dump rather than prose.

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 no explanation, and the description still covers the things structured fields do not: mutation semantics, the server-side download model, retry safety, quotas, and accepted file types. Nothing an agent needs to invoke this correctly is 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 coverage is already 100%, so the baseline is 3; the description adds real meaning on top by stating which parameters are required per action ('Required to add' via url, 'Required to remove' via attachment) and by explaining the reuse semantics of idempotency_key for lost-response retries. It does not clarify filename defaulting or the workspace-failure behavior, which the schema already covers.

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+resource pair in both modes ('Add a file to a task or remove one'), and the two action branches are clearly delineated with their own parameter requirements (url for add, attachment for remove). It also names the sibling used for the read path (task_show), so an agent can separate this tool from task_show without inspecting either 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?

Gives conditional routing for both branches, names the alternative for reading attachments ('Read a task's files with task_show and include: ["attachments"]'), and supplies concrete hard limits (10 attachments per task, 10 MB per file, allowed MIME types) that determine whether the call should be made at all.

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