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

Annotations declare a non-read-only, non-idempotent, open-world operation; the description adds the crucial behavioral context that isn't in structured fields: the credit cost floor (30 credits/image default model), the separate USD wallet for API keys, and the quote-before-charge confirmation protocol. It does not describe what happens on failure or whether a partially-spent quote expires.

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, front-loaded with the purpose before the billing mechanics. The dense billing sentence carries a lot at once (credits vs USD wallet, quote then confirm) but every clause is actionable and there is 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?

For a 6-parameter, cost-incurring, non-idempotent tool with no output schema, the description covers cost and approval well but says nothing about the return value — an agent can't tell whether it gets a finished image or a job handle to poll with get_job. The image vs image_url split is left entirely to schema descriptions.

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 the relational semantics the schema only implies: omitting the approval fields triggers quote mode, and max_credits vs currency/max_usd are mutually exclusive per auth type. It reinforces rather than duplicates the per-parameter docs.

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 specific verb and resource ("Change the lighting of a photo") plus three concrete examples of the transformation. An agent can distinguish relighting from sibling tools like apply_effect or edit_image by intent, though the description never names those alternatives explicitly.

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?

Gives a clear procedural rule: omit approval to get a quote, then confirm max_credits (OAuth) or currency + max_usd (API keys). It also tells the agent which billing path applies to which auth method. It stops short of saying when to pick this tool over edit_image or apply_effect for lighting-like effects.

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