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

Annotations cover only the safety profile (readOnly, non-destructive, non-open-world); the description adds everything that actually matters operationally: a concrete price (0.10 USDC on Base via x402 exact), a free tier (10 signed-wallet calls per rolling 30 days), the required X-Wever-Wallet-Proof binding to both the exact JSON arguments and the route, and the fact that no payment is signed or moved. It also discloses that the return is an Ed25519 signed receipt and points to the contract and human page.

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?

Purpose is front-loaded and every element (validation rules, cost, auth header, return type, contract link) is load-bearing rather than filler. The middle sentence is a long run-on list of checks, and the reference URLs at the end add length, but neither is padding.

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?

There is no output schema, so the description has to carry the return shape on its own, and it does at a reasonable level (a signed report marking each element present or missing, delivered as an Ed25519 signed receipt). Payment, auth, and endpoint details are all supplied, which is more than most definitions manage. The absence of any report field/format detail leaves a small gap for an agent planning to parse the response.

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% and the description largely restates the same field list the schema already documents (name, description, url, provider, version, skills, securitySchemes, capabilities) plus the JSON-object-or-text dual input, which the anyOf already encodes. The optional `label` parameter gets no mention in the description at all. Baseline 3 for a fully documented schema is the right landing point.

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?

Names a specific verb and resource ("check an A2A agent card") and enumerates exactly what is validated: HTTPS/public host addresses, skill id/name/description, authentication schemes, and boolean capabilities. That makes the tool's function unmistakable. It falls short of a 5 because it never names a sibling (e.g. wever_agent-identity-check or wever_mcp-server-check) to distinguish itself from the neighbouring checks, leaving the agent to infer the boundary from "round 2" alone.

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 you rely on the agent" gives clear timing context, and "preflight round 2" implies a sequence position. The negative scope ("no page fetch, no registry or chain lookup, no counterparty contact") implicitly routes live-fetch or registry tasks elsewhere. No explicit alternative tool is named, so it stops short of the 5 bar of when-not/alternatives.

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