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

Far exceeds the annotations (which only say idempotent, non-destructive, open-world). The description discloses cost behavior (credits held at start, refunded for unanimated shots, full refund on failure), the 409 price-change guard that charges nothing, runtime of 10-25 minutes with polling guidance, and concurrency/quota limits. This is exactly the operational context an agent needs before a paid, long-running mutation.

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-loads the highest-value facts — cost, prerequisites, quote-first — before secondary details, and every sentence carries non-obvious information. The density is achieved with comma splices and em-dash-free run-ons, which makes it slightly harder to parse than it needs to be, but nothing is 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?

For a 12-parameter, credit-charging, 10-25 minute async job with no output schema, the description covers everything an agent must know: what it returns (an id), how to retrieve the result (autoshort_get_video with {id: <returned id/videoId>, reporting status, stage, videoUrl}), how failures resolve financially, and how to avoid duplicate charges. Nothing material 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 coverage is 100%, so the schema already documents every field, which sets the baseline at 3. The description goes beyond it by tying parameters to workflow semantics: confirm+expectedCredits must match the quoted price or the call 409s, idempotencyKey prevents double-charging on retry, and plan-derived values (voice, language, style, look, outfit) mean most optional params should be omitted. That cross-parameter coupling is added meaning, though it does not restate the shots-vs-script tradeoff itself.

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?

Opens with a specific verb+resource ('Make the episode') and immediately constrains scope: 3-8 shots, 30-60 seconds, one recurring character, narrated captions. Sibling routing is implicit but clear — autoshort_quote_character_episode is named as the mandatory prior step, and the episode-creation boundary against autoshort_generate_video / autoshort_draft_video is legible from the season-plan requirement.

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?

States explicit preconditions (season plan REVIEWED + CONFIRMED, episode must match the plan), the mandatory quote-then-confirm sequence, and the exact error codes returned when preconditions fail (SEASON_PLAN_REQUIRED / SEASON_NOT_REVIEWED / EPISODE_NOT_IN_PLAN). Also names the alternative completion paths — poll autoshort_get_video with the exact argument shape, or use a webhook — and the rate limits (one at a time per account, 3 per day).

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