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

Goes far beyond the annotations: per-item credit pricing, all-or-nothing batch reservation before generation, 402 with zero charge on insufficient balance, fallback from failed clip to still frame with refunded clip credits. This is exactly the cost/risk disclosure an agent needs before a paid write.

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 action and the precondition, then pricing, then parameter semantics, then next step. Dense but nearly every clause carries operational value; the pricing sentence is long but non-redundant.

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 paid, mutating batch tool with no output schema, the description covers cost, atomicity, failure behavior, idempotency implications, and the polling path. It does not say what the immediate response contains (batch id / immediate vs queued status), which is the only real 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?

With only 25% schema coverage, the description carries most of the load and does it well: it explains variantIds vs variants, that setting/expression default to the latest previewed variant making them cheap re-captions, and that fromVariantId re-captions a rendered clip. Only the idempotencyKey is left to the schema, which already documents it.

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 concrete verb+resource+limit: 'Approve and render up to 20 variants'. It clearly separates this from autoshort_ugc_preview (drafts) and autoshort_ugc_get_campaign (polling) by naming both siblings.

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?

Explicit precondition ('Call ONLY after the user approved the preview'), an explicit choice rule between variantIds (approve drafts) and variants (new hooks / re-captions), and a follow-up instruction to poll get_campaign every 30 seconds. When-to-use and what-to-do-next are both covered.

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