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

Goes well beyond annotations: cost model (server-measured length × per-second rate × resolution), token-spend consent workflow, idempotency replay semantics ('REPLAYS the first job whatever the settings'), card/url fallback, and waiting behavior. No contradiction with destructiveHint=true or idempotentHint=false — the replay warning actually reinforces the non-idempotent claim.

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?

Telegraphic and front-loaded with labeled sections (WHEN, THE CARD, WAIT, COST, SPENDS TOKENS, IDEMPOTENCY), so it scans fast. It is dense and long — some cross-references to 'this server's instructions' consume space without adding local information, keeping it off a 5.

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 costly, destructive, open-world generation call with no output schema, the description covers prerequisites, consent/spend gating, waiting protocol, idempotency, return shape (job id, url fallback), and failure cases (other account's video refused, 3–10s limit). Nothing an agent needs is missing.

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 schema carries field-level meaning, but the description adds real usage guidance beyond it: how to price with `estimate_only: true`, that idempotency keys must never be reused, and that `720p` should be named in the priced ask. It does not repeat all params, which is correct.

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 transformation ('the SAME clip with the prompt's changes applied') and pins the invariant ('camera, timing and motion stay'), which cleanly separates it from generate_video/extend_video/reshot_video siblings. An agent knows exactly what this produces without opening the 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?

Explicit WHEN block with example utterances ('make it snow', 'put them in suits'), a prerequisite (read `get_recipe` `restyle` first), and a negative exclusion (do not call `show_generation` for this job). Follow-up protocol via `wait_for_generation` and the no-polling rule are spelled out.

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