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

Annotations only declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false; the description goes far beyond by disclosing the asynchronous pattern (returns job_id immediately, poll job_status, then get_moments), the billing model (spends Horizon Units equal to reading the whole video, higher cost is refused, failed searches are refunded, re-analysis is not recharged), and the idempotency mechanism via request_key. No contradiction with the annotations — the cost/spend behavior is consistent with readOnlyHint=false.

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?

Every sentence carries information — no filler — and the use case and examples are front-loaded before the parameter and cost details. It is somewhat crammed, packing routing, parameter hints, async flow, and billing into a dense block with little visual separation, which slightly hurts 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?

Despite an output schema existing, the description still explains the result shape (time ranges with a quote, sized by min/max_seconds) and, more importantly, the full multi-step lifecycle across job_status and get_moments plus how clip_range and find_clips consume the results. For a costly async tool with 7 parameters and 0% schema coverage, nothing an agent needs to invoke it correctly is missing.

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 it covers all seven parameters: project_id (from list_projects), topic (plain words), max_hu (approved amount, over-budget refused), count (1–10), min_seconds/max_seconds (default 20–60), and request_key (any stable string, reused only to retry). This adds substantial meaning the schema lacks, such as the source of project_id and the budget semantics of max_hu.

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 — semantic topic search over a long video, done before clipping — and backs it with concrete user-phrased examples ("where do I talk about the new game", "find the funny bits"). It explicitly separates itself from find_clips, clip_range, and search, so an agent can route correctly 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?

Opens with an explicit when-to-use trigger and includes a dedicated "Not for:" clause naming the two alternatives (find_clips, clip_range) and the name-search sibling (search). It also prescribes a prerequisite workflow — call estimate_hu for the same project first, show the number, pass the approved amount as max_hu — which is exactly the kind of usage guidance an agent needs.

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