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

Annotations declare the non-read-only, non-destructive profile, and the description goes beyond them by disclosing the async behavior: it returns a job per clip and requires a follow-up with get_job for the files. The prerequisite on get_episode readiness is also useful behavioral context. It stops short of describing limits or failure modes, so it is strong but not exhaustive.

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 use case and effect, then prerequisites and the alternative, then a brief parameter note. The sentence enumerating style, caption_size, position, hook_title, fit and background is somewhat duplicative of the schema, keeping it from a full 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 batch render tool with an output schema and annotations already present, the description supplies everything not covered elsewhere: the get_episode precondition, the restyle_clip exclusion, and the job/get_job follow-up flow. An agent has all it needs to invoke and chain correctly.

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 already documents all eight parameters including enum meanings. The description adds only the source of the clips values (numbers or refs from get_episode, refs in brackets fine) and the fact that the optional style/caption fields apply to the whole batch, which is marginal value over the structured data.

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 (cuts and renders clips) with the exact resource and effect (captions burned in, one step). It clearly distinguishes itself from restyle_clip and get_episode, so an agent can identify its role 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 trigger ('when the user picks found clips to make'), an explicit precondition ('do not use before get_episode reports the episode ready'), and an explicit negative route to a named alternative ('do not use to change a clip that is already made (use restyle_clip)'). Nothing is left to inference.

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