Create Outline

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

Strong disclosure beyond the annotations: statelessness (nothing persisted), the 10-credits-per-slide charge taken once before return, a 402 on empty balance, and 409 semantics for reused idempotency keys. The retry-safety note is consistent with idempotentHint=false, and nothing contradicts destructiveHint=true, though the description never explains what the destructive flag actually refers to for a tool that persists nothing.

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 paragraphs, purpose front-loaded, then prerequisites, then billing/retry. Every sentence carries distinct operational information (persistence, extraction readiness, price, error codes) with no filler.

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?

Return values are covered by the existing output schema, and the description supplies the side-effect, cost and retry facts an agent needs before calling. The only gap is the accept-language header parameter, which is undocumented in both schema and description.

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 71% schema coverage, the schema already documents prompt, sources, language, slide_count and level_of_detail in detail. The description adds genuine meaning only for the undocumented Idempotency-Key (retry safety, 409 on a key that already paid); accept-language gets no explanation anywhere, so it neither fully compensates nor adds much beyond the 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 states a specific verb and resource ("Generate a stateless outline") plus its input modes (prompt and/or extracted files), and the word "stateless" plus "No deck... is persisted" cleanly separates it from the create_presentation sibling. An agent can tell what this produces without opening the 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?

It gives real entry conditions (referenced files must be in the caller's workspace and already extracted) but never names an alternative sibling or states when to pick create_presentation versus create_outline, leaving the main routing decision to inference. Prerequisites are covered; exclusions are not.

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