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

With no annotations, the description carries the burden and does well: it discloses per-episode cost (€0.12), that billing is tied to the Bearer API key, that no video is rendered, and what the returned fields are. It stops short of latency, failure modes, or what happens if neither transcript nor audio_url is supplied.

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-loads the capability, then the negative constraint and handoff, then cost, then parameters. Every clause carries distinct information with no restatement of the tool name or 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 a stateless, zero-required-parameter inference tool with an output schema, the definition covers cost, output fields, input formats, and the sibling handoff. The only unaddressed edge is which input wins if both transcript and audio_url are provided, or what happens if neither is.

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 0%, so the description must compensate, and it does: transcript accepts plain text or JSON [{start,end,text}] segments, audio_url is audio/video and an alternative to transcript, and n is bounded 1-10 with default 5. This meaningfully exceeds the bare string-typed schema (which even types n as a string).

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 and resource ('Finds up to N standalone moments... worth cutting into short-form clips') and immediately delimits scope with 'Does not render video', which separates it cleanly from clip_cut_caption and video_clip among the siblings.

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?

Explicitly names the downstream tool to use instead ('feed the times into clip-cut-caption') and presents transcript vs audio_url as alternatives, so the agent knows both the handoff path and the input choice without inference.

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