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

Annotations only declare readOnly=false, idempotent=false, destructive=false, openWorld=true — they say nothing about cost, async behavior, or lifecycle. The description adds three things annotations cannot: that credits are spent, that a job id returns immediately rather than blocking, and that the job completes even without polling, which is critical for an agent deciding whether it must poll.

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?

Four short clauses: action, cost warning, return contract, lifecycle guarantee. Front-loaded with the action and the irreversible consequence (credit spend), and nothing is padding.

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 9-parameter, nested-object, credit-spending mutation with no output schema, the description supplies the essential missing context: cost, async return shape, and follow-up tool. It does not restate parameter constraints (already in schema) and has no output schema to explain away, so only minor gaps remain.

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 89%, so the schema already documents workspace key scoping, run_id, overrides fidelity, project media-pool behavior, and intent semantics in more depth than a description could. The description adds no parameter-level information at all, which is acceptable given the coverage but earns only the baseline.

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 and resource ('Clone a template into a real video generation') and implicitly contrasts with the sibling preview_generation by calling out that this produces a 'real' generation. An agent can distinguish this from render_video, preview_generation, and get_template 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?

Routes the agent to the follow-up call explicitly ('call get_generation to follow it') and signals the cost gate ('SPENDS CREDITS'), which tells the agent to be deliberate. It stops short of naming when NOT to use it (e.g. preview_generation as the free dry run), so it is strong context rather than complete routing.

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