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

Annotations only declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description adds genuinely new behavior: one-time URL, 15-minute expiry, 300MB ceiling, the exact multipart/form-data shape (fields entries then file last), and the returned uploadUrl/uploadId semantics. This is exactly the kind of operational context annotations cannot carry.

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?

Purpose, limits, and the three-step flow are front-loaded, and every clause carries operational weight. The inline curl example is dense but earns its place by pinning down the multipart ordering rule; it is the only slightly heavy element.

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?

With no output schema, the description compensates by naming what comes back (uploadUrl, fields, uploadId) and how to consume it. Combined with the expiry, size, and format constraints, an agent has everything needed to execute the full upload flow without guessing.

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 schema documents fileName, mimeType, and size. The description still adds meaning the schema lacks: a 300MB cap that bounds the `size` parameter and the accepted-format scope behind the mimeType enum. The format list largely repeats the enum, so it is not a full 5.

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 ('Get a one-time URL to upload a file from the user's device directly') and immediately bounds it with the 300MB limit and file-type scope. This distinguishes it cleanly from siblings like upload_media_from_url, upload_media_from_base64, and open_upload_box without needing to name them.

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 an explicit numbered workflow: call this, POST multipart to uploadUrl, then call finish_upload with the uploadId. That tells the agent precisely where this tool sits in the sequence. It stops short of explicitly stating when NOT to use it (e.g. server-side sources vs upload_media_from_url), so it is not a full 5.

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