Find Shorts in a long video

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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely non-redundant information by enumerating the returned fields (times, hook line, title, score) even though no output schema exists, and by describing the selection criteria for a good Short. It omits cost/latency of an AI analysis pass and failure behavior, 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?

Three short sentences, front-loaded with the verb and the output, then the input modes, then the pipeline hand-off. No filler. The parenthetical "(transcribed)" and the compressed list of input sources are slightly terse but not wasted.

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 definition covers purpose, return fields, input modes and next step, which is substantial for a six-parameter, zero-required tool with sparse schema documentation. Still missing: how to choose among the three source parameters, what `count` and `max_seconds` constraints produce, and any note about channel scoping or no-caption failures.

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 17% — just `channel` is documented. The description partially compensates by implying the three mutually exclusive source parameters (file_path vs video_id vs transcript_path), but it never maps them explicitly, and `count` and `max_seconds` are left entirely unexplained in both schema and description.

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?

Specific verb and resource: "Finds the moments in a long video that work as standalone Shorts," followed by the exact return shape (start/end times, hook line, title, score). It also names the sibling it hands off to (create_short), so it is distinguishable from create_short and analyze_video without opening a 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 names the three accepted input modes (local transcoded file, uploaded video's captions, transcript file) and states the follow-up step: "Then cut them with create_short." This gives clear context for when the tool is the right entry point, but it stops short of exclusions — e.g. it does not say what to do if the upload has no captions, or whether analyze_video should be run first.

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