process_episode

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

With no annotations, the description carries the behavioral burden and does well: it discloses asynchronous execution, returns { job_id } immediately, requires polling via job_status, and describes the eventual result shape. It still does not cover permissions, overwrite behavior, cost, or failure modes for a heavy mutation job, which keeps it below a 5.

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 front-loaded with the core pipeline, then immediately covers return behavior, polling, and the relevant alternative. Every sentence contributes operational information with no filler.

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 11-parameter tool with no annotations and no output schema, the description adequately explains the workflow and eventual result fields. However, it leaves most parameters undocumented and does not provide enough semantic guidance for choosing among the many enum options.

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 only 36%, and the description does not compensate by explaining the roles of top, crop, fast, engine, format, output, quality, language, transcript, or caption_style. It mentions ranking and rendering conceptually, but adds no meaning beyond the raw schema property names and enums.

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 states a specific compound action clearly: transcribe, rank moments, render clips, and write metadata for an episode. It also distinguishes this full pipeline from rank_clip_candidates when only a shortlist is needed, so an agent can identify the tool without opening its 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?

It explicitly defines the usage context as a one-shot episode job and names the alternative rank_clip_candidates for shortlist-only work that does not require rendering. It also directs the agent to job_status for polling after the immediate job_id return.

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