Quote a shot candidate

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

Annotations only declare readOnlyHint=true/destructiveHint=false; the description goes well beyond them by disclosing the billing model (a delivered candidate is charged one unit whether kept or discarded, a failed one costs nothing) and an explicit failure mode ('while shot candidates are closed it answers editing_disabled and charges nothing'). That is exactly the kind of side-effect and cost context an agent needs before firing a quoting call in a credit-metered system.

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 sentences, no filler, and the most decision-relevant fact (no credit spend) is front-loaded before the caveats. The middle clause about usable_until is compressed to the point of ambiguity, slightly undercutting the otherwise tight structure.

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 tool with a required nested oneOf operation across four distinct modes, 0% parameter documentation, and no output schema, the description covers behavior but leaves the invocation surface entirely unexplained. An agent knows what the call costs and when it is rejected, but not how to choose a mode or what take does.

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, yet it explains none of the four parameters: run_id, shot_id, take, and the operation oneOf with four undocumented modes (retake, new_picture, edit_picture, animate) are untouched. Worse, the only named term, usable_until, is not a parameter at all, which can misdirect an agent looking for input guidance.

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?

"Price one shot candidate WITHOUT spending credits" names a specific verb (price) and resource (shot candidate) and immediately states the defining constraint that separates it from create_candidate/generate-style siblings. An agent can tell this is a dry-run cost estimate 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?

The 'without spending credits' framing implies the intended use (cost-check before committing), and the delivery/failure charging rules imply what happens after quoting. However, no sibling is named as the alternative (create_candidate, quote_revision, quote_image all exist but are never referenced), and the 'usable_until' clause is cryptic without stating whether it is an input or a return value.

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