Capture transaction

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's 'Destructive write' partially restates that. However, it adds meaningful context by specifying the destructive consequence: funds are actually collected, making the operation financially irreversible. The 'Confirm before use' warning reinforces the destructive nature beyond the annotation flags.

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?

A single, front-loaded sentence that immediately signals destructive behavior, states the operation, and provides a clear warning. Every word earns its place, and the structure is highly scannable.

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?

With no output schema and no parameter descriptions, the tool definition is spartan. The agent knows the tool is destructive and collects funds, but it lacks crucial details about optional partial captures, idempotency, expected responses, or failure conditions. For a financial write operation, this is too incomplete for confident invocation.

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 must compensate for unexplained parameters. It does not mention the 'id' field, the optional 'amount' (which likely indicates partial capture), or 'idempotencyKey'. An agent receives no help understanding what each parameter means or how they interact, making this a significant gap.

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 ('capture'), a specific resource ('an authorized transaction'), and the concrete effect ('causing funds to be collected'). This clearly differentiates it from siblings like refund_transaction or cancel_transaction by describing the actual money movement that occurs.

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 phrase 'capture an authorized transaction' implies the tool is for transactions that have been previously authorized and are ready for fund collection. However, there is no explicit guidance on when to use this over refund_transaction or cancel_transaction, and no mention of preconditions beyond authorization. The warning 'Confirm before use' is a caution, not a usage rule.

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