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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add context, and it does: plan-based pricing gating and the incremental-read pattern for long videos. It stops short of covering edge behavior such as what happens if both clip_id and video_id are supplied or what an unavailable/paid-gated result looks like.

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 core purpose, then output modes, then cost/pagination caveats. No filler or redundant restatement of the title.

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?

With no output schema, the description correctly spells out the return shape (plain text vs SRT with timings), which is the most important missing structured information. It also covers the free/paid distinction and slicing behavior; only mutual-exclusivity and failure handling are left unaddressed, which is a minor gap.

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 100%, so all five parameters are already documented, including the clip_id/video_id either-or and the enum values for format. The description only adds that from_seconds/to_seconds are intended for reading long videos a part at a time, which is a modest supplement over the schema baseline.

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 uses a concrete verb and resource ('Returns what is said in a clip, or in a whole video') and immediately states the two output modes (plain text or SRT with timings). It also distinguishes the clip case from the whole-video case, which no sibling tool (get_clip, get_video, list_clips) does.

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 gives clear usage context: clip transcripts are free, whole-video transcripts require paid plans, and long videos should be read in slices with from_seconds/to_seconds. It does not explicitly name siblings such as get_clip or get_video as alternatives, but the clip-vs-video framing effectively routes the caller.

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