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

Annotations only declare the mutation profile; the description adds everything operationally important: single-use, project-scoped, one file, 15-minute vs 24-hour expiry, per-type size caps (MP4/MOV 100 MB, JPEG/PNG 5 MB), retry after a refused file, and deletion of unused files after 24 hours. It also warns 'never put the file in a tool argument', which prevents a likely misuse.

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 key distinction and the return value, and nearly every clause carries non-obvious information. The trade-off is density: the branching logic, limits, and expiry rules run together in one block rather than being separated into scannable steps.

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?

There is no output schema, yet the description fully covers what comes back (uploadUrl, uploadId), how long it lives, and how it is consumed downstream. Nothing an agent needs to call this correctly or explain it to a user 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 100% so the baseline is 3, and the description goes beyond it: forPerson is explained as changing both who uploads and the expiry window (24h vs 15m), and kind is implicitly tied to the format/size limits. It doesn't restate projectId, but the schema already sources it from list_projects.

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 and resource ('create an upload link'), the exact return value (a single-use uploadUrl), and draws a hard boundary against the public-URL case. An agent can distinguish this from create_post/create_reel/generate_image without opening any 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 explicit branching: if you have shell access, run the returned curl; if you don't (Claude.ai, blocked host) or the user holds the file, set forPerson: true and hand the URL over. It also names the downstream step (pass uploadId to create_post or update_post) and the verification sibling (get_upload says whether the file arrived).

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