Generate a video (billable)

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

Annotations only declare the generic profile (not read-only, open-world, non-idempotent); the description adds the operational facts an agent cannot infer: async semantics (returns task_id at once, minutes-long runtime), per-second billing including extra billed seconds for reference videos, and the approval gate. The client_request_id dedup note is consistent with idempotentHint=false rather than contradicting it.

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?

Five short sentences, front-loaded with BILLABLE and the endpoint, then the precondition, then the async/polling behavior. No filler and no repetition of the schema.

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 7-param, nested-object, billable async tool with no output schema, the description covers cost model, approval prerequisite, return shape (task_id), and the correct follow-up tool. An agent has everything needed to call it safely once.

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 100%, so the baseline is 3. The description still contributes cross-parameter semantics – that reference videos 'add billed seconds' and that model/duration/resolution/cost must have been approved – which links max_cost_usd and reference_video_seconds to the billing decision rather than restating their schema text.

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?

Opens with a specific verb+resource ('creates a paid video task') plus the endpoint (POST /v1/videos) and the billing basis (charged per second). The word 'video' plus the cost framing separates it cleanly from generate_image and the read-only siblings.

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?

Explicit preconditions: 'Only call after estimate_cost on the same input and the user's explicit approval of the model, duration, resolution and cost.' It also names the alternative for the follow-up step ('poll with get_task') and states a negative rule ('Never call again to check progress').

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