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

Annotations only declare readOnly=false, idempotent=false, destructive=false. The description goes well past that: it names the storage destination (Quiz.Video storage), the exact PUT protocol and header-matching requirement, the byte-exact body rule, per-kind size and duration limits (15 MB / 250 MB & 5 minutes / 50 MB), and the required follow-up call. That is the kind of operational detail an agent needs to complete a non-idempotent write.

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 action and the PUT-then-complete flow are front-loaded, and nearly every clause carries operational weight. It is dense, with limits and the music variant packed into trailing sentences, but no sentence is filler.

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 correctly names the key return elements (uploadUrl, returned headers, musicId for the music purpose), which is the essential part. A few response details, such as an identifier for library uploads, are left implicit, but nothing required for a correct call sequence 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 60%, and the description compensates for the weak spots: it explains that `size` must equal the exact body byte count, that `contentType` must match the PUT header, and that `purpose: "music"` yields a musicId for backgroundMusicId. `kind` is only indirectly covered through the per-kind limits, and `filename` is left to the schema, so it is strong but not exhaustive.

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?

The description opens with a specific verb and resource: 'Get a presigned URL to upload your own image, video or audio file.' It makes the two-step upload flow explicit and names the follow-up sibling quiz_video_complete_media_upload, so an agent can separate it from delete_media, list_media, or update_quiz_media 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?

It states exactly when to use it (uploading your own files), gives the mandatory next step, and includes a hard exclusion: 'quizzes can only use uploaded files, never outside URLs.' It also routes a specific sub-case, purpose 'music' for background tracks, and tells the caller what that variant returns.

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