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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the bar is lower, yet the description still adds real operational context: settlement_recorded is historical evidence and not proof of active service, and unknown/review outcomes require operator escalation. The one gap is that it never says what the call actually returns or whether it can fail, but with a non-destructive read that gap is minor.

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?

Roughly four sentences, front-loaded with the read statement, and each clause carries information, so it is not padded. But the phrasing is tangled ("without sending, observing the chain or repairing a payment") and the warnings are stacked without clear separation, making it slower to parse than its length warrants.

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 read with full annotations and no output schema, the description covers the essentials: what it reads, that it is passive, and how to handle ambiguous outcomes. It loses a point for not enumerating the possible status values beyond the incidental mentions of settlement_recorded and unknown/review, which the agent would need since there is no output schema.

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?

There is a single required parameter at 0% schema description coverage: handoffId, constrained only by a 64-character hex pattern with no human-readable explanation. The description refers to "this handoff" but never says the ID comes from create_wallet_handoff or that it identifies the handoff being inspected, so an agent must infer the linkage between the pattern and the sibling tool's output.

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 opening clause gives a verb and resource ("Read server-recorded settlement evidence for this handoff"), and the negative framing ("without sending, observing the chain or repairing a payment") separates it from submit_wallet_payment and prepare_wallet_signature. However, the description never plainly states that this returns the status of a wallet payment handoff, and the shift in vocabulary from "payment status" (name) to "settlement evidence" leaves the agent to bridge the gap.

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?

Usage is only implied: read this to inspect recorded evidence rather than to act, and do not treat it as a trigger to resend. There is no explicit "use this when you need X; use sibling Y when Z" routing despite eight sibling tools including submit_wallet_payment and prepare_wallet_signature. The closing rules ("Unknown/review results require operator review", "Never resend automatically") govern post-call behavior rather than tool selection.

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