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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with concrete detail: it reads only call material, contacts nobody and moves no money, it is idempotent-ambiguous but returns an Ed25519 signed receipt, and it costs 0.10 USDC per call on Base via x402 with 10 free signed-wallet calls per rolling 30 days. That pricing and auth surface (X-Wever-Wallet-Proof bound to the exact JSON arguments and route) is real behavior an agent cannot get from the annotations. The only blemish is that a per-call USDC charge sits somewhat awkwardly against the blanket 'no money movement' phrasing.

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 core capability and the checks performed are front-loaded in the first two sentences, and the rest is operational detail. Some tail matter (contract path, human page URL) is administrative rather than decision-relevant, and the payment/wallet-proof block is dense, but no sentence is pure filler.

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 paid, signed-report tool with no output schema, the description gives enough to call it correctly: input limits, what gets flagged, per-currency annual and monthly equivalents, and the signed receipt. What is missing is any sense of the report's structure or error behavior (e.g. what a failed wallet proof or partial-input rejection looks like), which an agent would otherwise need.

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 100%, so the schema already documents as_of, stale_grace_days and every subscription field. The description adds only marginal semantics, noting that prior amounts and charge dates may be supplied 'when known' so cadence and increase checks can run. It does not explain the as_of or stale_grace_days defaults, which the schema covers anyway, so baseline 3 holds.

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 states a specific verb and resource: submit up to 200 subscriptions or recurring charges and get back a signed audit report flagging duplicates, price increases, cadence deviations, double charges and stale charges. It also names the endpoint (POST /api/subscription-audit) and the exact checks performed. It never differentiates itself from the close sibling wever_subscription-rail or from wever_diligenceops-paid-run, so an agent must infer the boundary.

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 implied rather than stated: the agent learns what material to send and that prior amounts and charge dates improve the analysis 'when known', but there is no explicit when-to-use vs an alternative, no prerequisites, and no statement of what input is unacceptable. The scope constraints ('no page fetch, no account access, no merchant contact') imply the tool only works on the caller-supplied data, which is useful but is framed as a limitation, not as routing guidance.

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