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

Annotations declare this is a non-destructive, non-idempotent, non-open-world write, and the description adds genuinely new behavior: the call only mints a link, the upload_url expires in one hour, and it returns media_id plus a ready-to-run curl command. That tells the agent the file transfer happens outside the tool, which is the key non-obvious trait. It stops short of saying what happens to the media if the link expires unused or whether a repeat call creates a duplicate, which matters given idempotentHint=false.

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?

Three short sentences, no filler, with the core action and the sibling handoff front-loaded before the return-value detail. Every clause carries information the agent acts on.

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 three-parameter tool with a full output schema, the description covers the action, the constraint (format/size), the return contract (media_id, one-hour URL, curl command) and the explicit non-behavior. Nothing an agent needs in order to call it and chain into schedule_post is absent.

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 description coverage is 100%, so bytes, file_name and content_type are already fully documented, including the 1 GB cap and the MP4/MOV enum. The description restates the format and size limits but adds no new meaning — notably it says nothing about file_name's role beyond what the schema states, nor why byte size must be supplied up front.

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 ('Make an upload link for a finished video file') and immediately scopes it against the downstream sibling by naming schedule_post mediaId. The final 'Does not post.' removes any ambiguity about what this tool does versus the posting tools in the sibling list.

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?

Clear context: use this when the user already has a finished video file and wants it posted, then pass the result to schedule_post. The 'Does not post' line establishes the boundary with the posting sibling. What's missing is routing against the other ingest tools (import_media, import_asset) for non-post-bound uploads, so the agent must infer which intake path applies.

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