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

Annotations only declare the mutation/idempotency profile; the description goes well beyond by disclosing the required `write` scope, that the URL is single-use and short-lived, that raw bytes must be POSTed with the file's Content-Type, that the response carries a `storageId`, and that a 413 means the account's storage is full. That is exactly the operational context an agent needs and cannot get from the 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?

Front-loaded with the scope tag and the one-line purpose, then organized as numbered steps, so an agent can stop reading at the point it has enough. It is dense — backticked field names, a full curl example, and an endpoint note packed into a single paragraph — but essentially every clause carries actionable information.

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 zero-parameter tool with no output schema, the description covers the entire lifecycle: how to get the URL, how to upload to it, what comes back, where to pass the result, and the one failure mode (413, storage full). Nothing an agent needs in order to call 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?

With zero input parameters there is no parameter meaning to add, so the baseline applies. The description usefully explains the request body contract (raw bytes plus Content-Type) and the identifiers returned, which substitutes for parameter detail here.

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 ('Get a media upload URL', 'Step 1 of attaching a LOCAL file ... to a draft') and immediately scopes it to local files, distinguishing it from the web-URL path handled by videoUrl/imageUrl. An agent can tell exactly what this does and what it does not do without opening another 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-to-use (local video/image/audio for a draft), when-not-to-use (media already on the web — pass videoUrl/imageUrl instead), and a named alternative destination (music_tracks_create for music-library audio). It also spells out the full three-step sequence with create_content/update_content, 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.