transcript_find_clips

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

With no annotations, the description carries the full burden and does well: it discloses the scoring heuristic, the sentence-boundary constraint, non-overlap, and critically that returned ffmpeg/crop commands are returned rather than executed and that nothing is written to disk. It omits auth requirements, rate limits, and failure modes, which keeps it short of 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?

Front-loaded with the core purpose, then constraints, then return contents, then the critical 'commands are returned, not run' caveat. Four sentences with little waste; the parenthetical clarification about mid-clause moments is the only slightly verbose passage.

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?

An output schema exists, so the description need not enumerate return fields, yet the parameter side is entirely uncovered and the dest_dir/'nothing written to disk' tension is left unresolved. For a 5-parameter tool with no annotations and no schema descriptions, this leaves real gaps for an agent to guess at.

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 0% for all five parameters. The description never explains count, min_s, max_s, or dest_dir; the dest_dir parameter is especially ambiguous given the claim that 'nothing is written to disk', yet the description does not reconcile this. Only job_id's role is inferable from context.

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 ('Find self-contained, high-density moments worth cutting into clips') and immediately defines the selection criteria (words per second, sentence-boundary alignment, non-overlap). This is clearly distinct from sibling operations like transcript_search or transcript_segments, which do not produce clip candidates.

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 criteria for what counts as a clip (sentence-bounded, dense, non-overlapping) is spelled out, which implies when the tool is appropriate. However, there is no explicit when-to-use versus alternatives such as transcript_search, and no mention of prerequisites (e.g. that job_id must reference a completed transcription job).

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