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

Annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) cover only the safety profile, but the description adds substantial context: no provider work, callbacks, document retrieval or signed attestations; no authority granted and no server credentials supplied; existing credentials/mandates/action grants still required; pricing (1.00 USDC on Base) and the 10 free signed-wallet calls per rolling 30 days; and a pointer to the 402 body for x402 terms.

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 purpose sentence is buried mid-paragraph behind pricing and endpoint details, so the description is not front-loaded. Free-tier information is repeated ('Free computation: /api/mcp or /api/service-resolver' and again 'the Labs MCP and resolver computation paths remain free'), and the operating-boundary paragraph restates the caller-supplied-data point.

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, closed-world-of-supplied-data computation with no output schema, the definition covers payment, auth prerequisites, rate limits, negative boundaries and match semantics well. It is close to complete; only the per-parameter meaning of the two evidence arrays is left implicit.

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 for the two top-level arrays is 0%, so the description must carry semantics. 'Compare explicit submitted evidence labels and return exact matched and missing items' does convey exact-match comparison semantics, but it never explains the distinction between expected_evidence and available_evidence, nor the optional/required asymmetry (available minItems 0 vs expected minItems 1) visible only in the schema.

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+resource: compare explicit submitted evidence labels and return exact matched and missing items, plus a clear negative scope ('does not read or verify document contents'). It distinguishes itself from document-reading tools, though it never names a specific sibling such as wever_mcp-diligence-rail or wever_return-package-viewer that an agent must choose between.

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?

It identifies alternative computation paths ('/api/mcp or /api/service-resolver', Labs MCP and resolver remain free) and the paid vs free tier split, which is useful routing context. However it gives no explicit 'use this when X, use sibling Y when Z' guidance, so the agent must infer when this paid run is preferable to the free computation paths or the diligence siblings.

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