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

The description does add genuine context beyond annotations (sandbox/demo nature, that unavailable/non-JSON backends raise tool errors, that backend status is surfaced). However, it repeatedly reassures that it 'grants no authority', 'never supplies server credentials' and 'does not verify', which reads as a harmless read-only inspection while annotations declare readOnlyHint=false and destructiveHint=true. This mismatch between the reassuring framing and the declared side-effect profile is the main defect.

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?

It opens with a caveat ('Unavailable historical backend') instead of the action, and repeats the 'grants no authority / no server credentials' disclaimer across multiple sentences. The return-field list and the no-verification disclaimer are also in tension, adding noise rather than front-loaded signal.

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, the description does enumerate expected return fields (verified, pending, approved, allowed rail, amount, expiration, run permission) and covers error/backend behavior, which is useful. But for a POST proxy with an opaque schema and destructive annotations, the contract is still insufficiently pinned down and internally inconsistent.

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% and the single 'mode' property is an open-ended, additionalProperties body with no enum or format detail. The description says 'Take a payment reference', which does not map onto the documented 'mode' parameter, so it neither compensates for the coverage gap nor clarifies how to populate the body.

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 does state a core action ('classifies payment-reference text', 'Inspects a submitted optional authority reference'), but it buries that under hedging and self-contradiction (first says it does not verify payment/expiry/mandate, then lists 'verified' and 'expiration' as outputs). It never distinguishes itself from siblings like wever_ap2-mandate-gateway or wever_delegated-authority, so an agent cannot confidently route to it.

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?

There is no when-to-use guidance versus the many sibling authority/payment tools, and no prerequisites or exclusions are stated. The closest thing is the vague 'Operating boundary' sentence, which describes what it returns rather than when to pick it. An agent is left to guess the trigger conditions.

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