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

Beyond the annotations (readOnlyHint=false), the description conveys that the operation is asynchronous and that status must be checked via polling. It also exposes a required auth scope ('jobs:write'). It stops short of describing the full state transition or response shape, but adds meaningful behavioral context.

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, each carrying distinct information: the action, the follow-up, and the required scope. The primary verb is front-loaded with no 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?

For a one-parameter tool with a clear async workflow, the description is nearly complete: it names the action, gives the polling endpoint, and states the scope. It could be more explicit about prerequisites or how the job_id is obtained, but these are inferable from the workflow and sibling tools.

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?

The sole parameter job_id is fully described in the schema as a ULID, so schema coverage is 100%. The description does not add parameter-level details beyond the schema, matching the baseline for well-documented parameters.

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: 'Queue the uploaded video for analysis.' It clearly identifies the operation and distinguishes it from upload/complete actions, though it does not explicitly name a sibling or state what this tool is not.

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 provides the next step ('Poll GET /jobs/{id} for status') and implies the tool is used after a video is uploaded. It doesn't explicitly list when not to use it or name alternatives like create_job, but the async workflow context is present.

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