live_find_clip

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

With no annotations, the description carries the full burden, and it does disclose 'Side effects: none' plus a note that returned path-ids are fresh rather than cached. It stops short of clarifying match multiplicity (first match vs all matches), whether session and arrangement clips are both searched, or what a result element contains, which are the behaviors an agent most needs here.

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?

Four short lines with the core purpose front-loaded, then side effects, an example, and an edge case. No filler or repetition; each sentence adds a distinct fact.

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?

There is no output schema, so the description must describe the return value, and 'fresh path-ids' only partially does so — the shape and contents of the match list are unstated. It also leaves open whether arrangement clips are searched, a meaningful gap given the many arrangement/clip siblings.

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 largely does: it defines query as a case-insensitive name substring, and the example live_find_clip(0, "verse") fixes the positional order of track_index and query. It does not explain what track_index indexes into or how to obtain it (e.g. from get_track_list/live_find_track), leaving one parameter partially under-specified.

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 clip slots in a track'), the matching rule (case-insensitive name substring), and what comes back (fresh path-ids). The scope within a single track separates it from the session-wide listing siblings, but it never names an alternative finder like live_find_track or live_find_device to make the boundary explicit.

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 matching semantics and the inline example imply when this tool applies (resolving a clip you know by name), and 'no match is a valid empty result' preempts a common agent confusion. However, it gives no explicit when-not guidance against siblings such as get_clip_summary, diagnose_clip_targets, or get_arrangement_clips, so selection still requires inference.

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