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

Beyond the annotations (non-readonly, non-idempotent) it discloses the credit-charging model, that the request is rejected when the cost exceeds max_credits, an expected duration of about 20 seconds, and the non-idempotency hazard with a concrete remedy. That is exactly the behavioral context annotations alone cannot 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?

Four sentences, each carrying distinct operational content: what it does, how to scope it with the user, the price gate, and runtime/retry behavior. Prerequisites are front-loaded and there is no restatement of the name or title.

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, slow, non-idempotent mutation with no output schema, the description covers cost, scoping, latency, and retry safety well. The one gap is that it never says what the call returns (presumably a shoot identifier to pass to get_shoot), which the agent must infer from the follow-up instruction.

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 baseline is 3, but the description adds real meaning for max_credits as a price the the user must have agreed to and a hard refusal threshold rather than a mere integer bound. It also frames pack as priced via get_pack. The options object is left entirely to the schema, which keeps it slightly below a 5.

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?

"Starts a shoot of a pack from the user's saved selfies, paid from their credits" gives a concrete verb, resource, input source, and cost model in one clause. It also distinguishes itself from get_shoot (polling) and get_pack (pricing) by reference, so an agent can route correctly without reading any 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 states an explicit precondition (tell the user the price first and pass it as max_credits), a conditional workflow (offer the whole pack or only chosen shots unless the user has already said), and recovery guidance (if a call got no answer, check list_photos before retrying). Alternatives are named by tool, not left to inference.

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