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

Annotations declare readOnlyHint=false and destructiveHint=false, so the caller knows state may change but nothing is destroyed. The description never says what actually changes: whether a payment record is created, claimed, marked as reconciled, or merely looked up, nor what happens when no payment exists. Framing it as 'Finds' sits in mild tension with the non-read-only annotation, though the 'so the work does not run again' clause partly reconciles this as idempotent recovery.

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 sentence with the action front-loaded and the rationale trailing, with no filler. Its brevity is appropriate, though the compression contributes to the ambiguity noted elsewhere.

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 non-read-only, one-parameter recovery tool with no output schema, the description should state what a successful call yields and what happens on a miss or repeat call. It says none of this, leaving the agent unable to predict the effect of invoking it, especially against the similarly named get_find_commerce sibling.

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 carries the full burden for find_id, and it never mentions the parameter at all. 'For a run' is the only hint about what the identifier denotes, and it is ambiguous between a find, a run, and a payment reference. No format, source, or behavior on a miss is provided.

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 gives a verb ('Finds') and an object ('a payment that already happened for a run'), so the intent is roughly graspable. But the vocabulary mixes 'payment', 'run', and 'commerce'/'find', and it never distinguishes this from the sibling get_find_commerce, which sounds like it retrieves the same payment data. An agent cannot tell the two apart from the text alone.

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 clause 'so the work does not run again' hints at an idempotency use case, which is the only usage signal present. There is no statement of when to call this instead of get_find_commerce, prepare_reconciliation, or apply_reconciliation, and no preconditions or exclusions. The agent must infer the scenario from a single subordinate clause.

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