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

Adds substantial behavior beyond the annotations: asynchronous job semantics (returns job_id immediately, runs for minutes), the polling contract, the caveat that num_clips is a ceiling not a guarantee, and the billing implication (consumes the account's clip balance). A non-idempotent mutation with openWorldHint is well characterized by this.

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-loads the core action and output format in the first sentence, then covers async lifecycle, the num_clips caveat, and billing in short clauses. 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?

Despite having no output schema, the description states what is returned (job_id) and the next step (poll get_job), and covers cost and duration. For a 14-parameter async job-creation tool this is complete enough to invoke correctly.

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 93% schema coverage the schema already documents nearly every parameter, so the baseline is 3. The description adds one genuinely non-obvious semantic — num_clips is a maximum rather than a guaranteed output count — which is not derivable from the schema and prevents a misread of results.

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 (cut a video link into vertical 9:16 short clips with burned-in subtitles) and enumerates the supported source platforms. An agent can distinguish it from list_clips/get_options without opening a 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?

Explicitly says the call only starts a job and that the caller must poll get_job until status is "completed" or "partial", which names the follow-up tool and condition. It does not cover when NOT to use this tool (e.g. vs list_clips), so it stops short of full routing guidance.

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