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

Annotations already declare readOnly, idempotent, and non-destructive, and the description reinforces compatibility by framing the action as 'Recommend' rather than execute. It adds non-obvious traits: deterministic behavior, evidence-bounded reasoning, signed output, and a 0.005 USDC cost, none of which appear in the schema. No contradiction with readOnlyHint.

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?

At roughly 18 words, it is extremely economical and front-loads the main purpose before behavioral traits. The standalone '0.005 USDC' fragment and clipped 'Deterministic, evidence-bounded and signed' read as bullet points, which is slightly awkward but not padded.

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?

The tool is simple to invoke with no required parameters, has an output schema, and has strong annotations, so the description does not need to explain return values or safety. It supplies the missing selection context—when to use it, for what input condition, and what behavior to expect—but leaves 'bounded', 'evidence-bounded', and 'signed' unexplained for less domain-aware agents.

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?

With zero named parameters and 100% schema coverage, the schema imposes no burden, so the description does not need to explain parameters. It adds an operational detail (the USDC cost) but no input syntax, which is acceptable because the input schema is open and effectively parameterless.

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 opens with a concrete action ('Recommend bounded recovery') and adds a second specific behavior ('reconcile ambiguous payments before retry'). It is distinguishable from siblings like transaction_recovery or payment_diagnose because it scopes to ambiguous payments and pre-retry recommendations, though it relies on jargon such as 'bounded' and 'signed' and does not name a comparison sibling.

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?

'Before retry' supplies an explicit timing condition and 'ambiguous payments' identifies the target scenario, so an agent knows when to reach for this tool. It does not enumerate exclusions or name alternatives, so it is clear context rather than full routing guidance.

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