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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false, idempotentHint=false), so the bar is lower, and the description adds real value beyond them: the state effect (order.status -> confirmed), that value then counts against the credit limit, and the precise exposure formula (open AR plus uninvoiced confirmed value). It does not say whether a retry is safe or how to undo a confirmation, which is the remaining gap for a non-idempotent mutation.

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?

The core action and the gate are front-loaded in the first two sentences, and the effects line is a compact, scannable trailer. The middle passage drifts toward policy commentary ('a refusal recorded in the log is worth more than an order'), which is behaviorally useful but slightly editorial for a tool definition.

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 one-parameter mutation with no output schema, the definition covers what the agent cannot get elsewhere: the credit-check semantics, the failure protocol, and the resulting state change. Nothing needed to call it correctly is missing, and the absence of a return schema means no further output documentation is owed.

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% with a single required order_id, and the schema already says 'The order to confirm. An existing order id.' The description adds no further constraint on the parameter (e.g., which order states are eligible), 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?

"Accept the order into the books. Runs the credit check." gives a specific verb (confirm/accept) and resource (order) plus the distinguishing mechanic (credit gate). It does not name the adjacent steps (o2c_accept_quote, o2c_ship_order, o2c_amend_order) explicitly, so sibling routing relies on the agent inferring the O2C flow, but the 'only credit gate' framing still singles it out clearly.

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?

Strong negative guidance: on failure, do not split the order, raise the limit, or invoice early — report the shortfall. That is an explicit when-not-to-work-around rule with named alternative workarounds being ruled out. It stops short of stating when to choose this over the surrounding O2C steps (e.g., that the order must already exist and be accepted), so it is clear context without full alternative routing.

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