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

Annotations already establish the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, closed-world). The description adds traits annotations cannot express: the output is deterministic, evidence-bounded, cryptographically signed, and costs 0.005 USDC per call. This is real added value, though it omits what the signature guarantees or what happens on non-ambiguous failures.

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 action statement is front-loaded and the whole entry is two short fragments, so scanning is fast. The stray ";" after "retry." and the mid-sentence price fragment make the structure slightly rougher than it needs to be.

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?

An output schema exists, so return values need not be described, and the annotations cover safety. What remains opaque is the input model: the schema is open (additionalProperties=true, no named fields beyond an example), and the description never explains what recovery actually operates on or how a caller prepares the transaction/failure payload.

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?

The context reports 0 declared parameters, so the baseline of 4 applies. The only input signal is an example object, which the description does not interpret; it neither clarifies the shape of the `transaction` payload nor what `ambiguous_payment` toggles, but with no named parameters there is little for it to compensate for.

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 names specific actions (recommend a bounded recovery, reconcile ambiguous payments) and the resource (ambiguous payments), so the agent knows the tool produces a recovery recommendation rather than executing one. It does not, however, distinguish itself from the near-identical sibling `transaction_recovery`, which appears to cover the same ground.

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" gives an implicit trigger condition, so an agent can infer this runs after a failure but prior to a retry attempt. There is no explicit when-not guidance and no named alternative (e.g., `payment_diagnose` or `payment_receipt_reconciler`) for cases where reconciliation is not the right move.

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