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

Goes well beyond the annotations, which only say this is non-read-only, non-destructive, and non-idempotent. The description discloses the one-time token model, a 10-minute expiry, that one token permits exactly one request, and how to batch multiple files via additional -F media=@path arguments — all operationally critical details absent from structured fields.

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 core constraint (no file bytes, returns a curl command) is front-loaded, and every following sentence adds a distinct operational fact: file-path substitution, where the URL appears, batching, retry, expiry. No sentence is redundant with another or with the schema.

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?

The tool has an output schema, so return values need no explanation, and the description instead covers the full two-step workflow an agent must execute — the only real complexity here. Nothing needed to invoke it 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?

There is a single parameter (project_id) and schema description coverage is 100%, with the schema already stating it must be a UUID of a project owned by the authenticated user. The description adds no parameter-level detail, so the baseline 3 applies rather than a higher score.

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 ('Prepare an upload into the project media library') and immediately distinguishes itself from write-style siblings by declaring 'This does not accept file bytes.' An agent can tell this apart from projects_files_create or projects_media_read 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 when-and-how: call this first, then run the returned curl command with __FILE__ replaced. It also names concrete anti-patterns ('do not base64-encode', 'do not put file contents in this tool') and a retry path ('If the upload fails, call this tool again'), leaving nothing to inference.

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