Regenerate narration

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

All annotations are false, so the description carries the full burden of behavioral disclosure. It reveals that the operation is a paid adaptation run, consumes rerender quota, requires fresh QA, and is an audio_and_video cascade. These are significant behavioral traits that affect cost, resources, and downstream workflows, going far beyond what the schema or annotations indicate.

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?

The description is concise and well-structured: first the main action, then usage condition, then consequences. Each of the three sentences adds distinct value without redundancy. It is front-loaded with the most important verb and resource, making it easy for an agent to quickly grasp the tool's purpose.

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?

The description covers key operational context: trigger conditions, cost (paid), quota consumption, QA requirement, and the cascading nature of the operation. It does not explicitly state return values or error handling, but given the tool's complexity and the absence of an output schema, the description gives enough context for an agent to choose and invoke it appropriately. Additional details on outcomes would push it to a 5.

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 67% with generic descriptions for jobId and sourceRunId. The description adds meaning by mapping the trigger enum to real-world conditions: 'explicit user request' for user_requested and 'get_job_status recommends retryTarget tts' for verifier_recommendation. It also implies sourceRunId is the run whose brief is unchanged, adding context that helps agents select the correct run.

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 clearly states the tool's function: regenerating narration from the unchanged durable brief and then its dependent video. It specifies the resource (narration and video) and the action (regenerate), and the cascade nature distinguishes it from simpler siblings. The explicit mention of 'paid adaptation run' adds a unique qualifier that sets it apart from other regeneration tools.

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?

The description gives explicit usage conditions: 'Use only on an explicit user request or when get_job_status recommends retryTarget tts.' This is clear guidance on when to invoke the tool. It does not explicitly list alternative tools or when-not conditions, but the referenced get_job_status recommendation provides a specific trigger that differentiates from normal retry or edit paths, so the context is strong.

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