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

Annotations only declare readOnly=false/openWorld=true/destructive=false; the description carries far more weight by disclosing the coin-spend mechanics (exact expected_cost, nothing charged if price changed, reservation of at most that amount, full refund on failure, partial settlement), the hosting requirement for media, and the retry/idempotency behavior. These are the traits an agent genuinely cannot infer from the structured fields.

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-loaded with the action, then cost, then media constraints, then result handling — a logical order with no filler sentences. It is dense and a couple of points (idempotency_key retry semantics, media hosting) are stated twice across the description and schema, which slightly dilutes the otherwise tight prose.

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 21-parameter, paid, long-running generation tool with an output schema, the description covers everything an agent must know before invoking: pricing contract, payment source constraints, media provenance, and how to obtain the result. Return-value detail is correctly delegated to the output schema.

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 baseline is 3, but the description adds real meaning beyond the schema: it pins expected_cost to the estimate_generation answer and explains the charge/refund consequence of a mismatch, and it states the idempotency_key retry contract rather than just describing the field. The per-kind semantics of the other 19 params are left to the schema, which already documents them well.

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 concrete verb+resource set ('Make an image, a video, a spoken script or a song') that maps directly to the kind enum, and it names the sibling tools it depends on (estimate_generation, get_generation, import_media). An agent can immediately separate it from estimate_generation (pricing only) and get_generation (polling).

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 routes the agent: get the price via estimate_generation and pass it as expected_cost, poll get_generation for the result, import off-host media with import_media first, and repeat idempotency_key on retries. It also states when NOT to expect an exemption ('a Relax queue or an unlimited allowance does not apply through an agent').

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