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

Goes well beyond the annotations: discloses the credit refund-on-failure and re-charge-at-current-price behavior, with per-tool prices, plus the async immediate-return semantics. The only minor tension is that idempotentHint=false while the schema exposes an idempotency_key — the description never resolves how those interact, though it does not contradict the annotation outright.

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 and its preconditions, and every clause is functional. The parenthetical price enumeration (story 8, transformation 14, clips 3, clip 2, compilation 8) is the densest part and could be deferred, but it is cost information an agent may need before charging a user.

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 an async, credit-charging mutation with no output schema, the description covers the prerequisites, the billing model, the failure modes, and the exact next step. Nothing an agent needs in order to call it safely 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 description coverage is 100%, so both parameters (project_id and idempotency_key, including the 24 h dedupe window) are already fully documented in the schema. The description adds no additional parameter-level meaning, so the baseline 3 applies.

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 ('Run a failed project ... again') and immediately narrows scope with preconditions (status "failed", retryable=true) and the supported project types (story, transformation, clips, clip, compilation). An agent can distinguish it from create_short/generate_clips 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?

Gives an explicit pre-call check ('Check errorCode first') and enumerates the exact error codes that make a retry pointless, which is a genuine when-not-to-use rule. It also directs the follow-up flow ('Returns at once — then wait_for_project'), routing the agent to the correct sibling for polling.

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