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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the two traits an agent most needs: the call spends credits and is refused with nothing charged when over budget, and it returns immediately as an async job rather than producing a result. That polling contract is stated outright.

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, each carrying distinct information: spend, refusal condition, and async follow-up. The call pattern (get_generation) is front-loaded in the final clause where an agent needs it.

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?

This is a complex, chargeable, asynchronous tool with nested inputs and an output schema, and the description covers the spend/refusal contract and the polling requirement. Return-value details are correctly left to the output schema.

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 all six parameters including the nested references object are already documented; the description nonetheless adds real meaning by explaining that max_credits is a quote-based spend ceiling with refusal semantics rather than just an integer field.

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 ('Start a generation') plus the resource it consumes (the user's credits), which distinguishes it from quote (pricing) and get_generation (status) among the siblings.

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 clear context: the call is refused when the quote exceeds max_credits, and it explicitly routes follow-up to get_generation until success or failure. It stops short of naming the quote sibling as the way to discover cost before calling, so the alternative path is only implied.

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