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

Goes well beyond the annotations: it discloses Horizon Unit spend, that a cost above max_hu is refused, that a failed job refunds the user, that unsupported options are refused by name, and that request_key is reused only for retries. It also describes the async lifecycle (returns job_id, poll job_status, then list_clips or explain_clips), which the annotations do not convey.

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 trigger and the outcome before parameter detail, and nearly every clause carries information. It is a dense block of prose for a 20-parameter tool, with the parameter explanations run together rather than structured, which costs a bit of scannability.

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 20-parameter, expensive, asynchronous mutation tool, the description covers preconditions (estimate_hu + approval), cost behavior, option defaults, and the full follow-up path to results. An output schema exists, so the absence of detailed return-field documentation is not a 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 0%, so the description carries the full burden and does: it defines project_id, count (1-10, default 5), range_start/range_end in seconds with 0 = all, topic as spoken words, min_seconds/max_seconds with effective 20-45 defaults, and clipping_preset semantics including 'none'. Every boolean switch is named under 'off unless asked', and max_hu plus request_key get behavioral meaning (cost ceiling, retry-only reuse).

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+resource (find moments and cut them into vertical 9:16 clips with word-by-word captions) and grounds it in user phrasings like "turn my VOD into TikToks". It explicitly separates itself from find_moments (meaning-based search), clip_range (one exact stretch), and edit_clip/style_clip (changing a finished clip).

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?

Gives an explicit trigger (user wants clips cut from a long video), a named 'Not for' list with the correct alternatives for each case, and the topic-vs-find_moments rule. It also spells out the prerequisite workflow: call estimate_hu, tell the user the number, run only after approval.

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