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

Annotations only declare non-read-only, open-world, non-idempotent, non-destructive. The description adds substantial context beyond that: the request is handled asynchronously by a human via email, the tool does not itself decide the refund, and it requires the 'support:write' permission.

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?

Two tight sentences with no filler; the action and its trigger are front-loaded, followed by the outcome mechanics and the permission requirement. Every clause carries information.

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 two-parameter, no-output-schema tool whose annotations cover the side-effect profile, the description covers purpose, trigger, handling path, and permission. It could add what the agent gets back after submission (e.g., a request id or confirmation), but nothing critical is missing.

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 100% and both parameters (reason, generationId) are documented in the schema, including the pointer to my_generations. The description adds no syntax or format detail beyond what the schema already provides, so the baseline 3 applies.

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 ('opens a request for credits to be returned') plus the triggering condition ('when a generated photo did not look like the person'), so an agent can tell this apart from my_credits or my_generations. It does not explicitly differentiate itself from the sibling contact_us, which is a plausible alternative for reaching human support.

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 description gives a clear use condition tied to bad photo output, and notes that a human answers by email and that the refund policy decides the outcome. It stops short of naming when NOT to use it or which sibling to prefer for other support needs.

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