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

Beyond the annotations it discloses the payment model (0.10 USDC on Base via x402 exact, ten signed-wallet free calls per rolling 30 days), the auth requirement (X-Wever-Wallet-Proof bound to the exact JSON arguments and tool route), the read scope (no page fetch, account access, merchant contact, or money movement), the receipt type (Ed25519), and a candid limit on matching semantics. This is exactly the kind of context annotations cannot carry.

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, then output, then payment/auth, then scope, then limits: the ordering is sensible and front-loaded. It is dense and runs to seven sentences with some clausal pile-ups, but each sentence carries a distinct fact (price, proof binding, matching limits), so little is wasted.

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 still tells the agent what comes back (a signed report quoting the sentences behind each finding, plus an Ed25519 receipt), what it costs, how to authenticate, and what the tool deliberately does not do. Nothing needed to call it correctly appears to be missing.

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 coverage is 100%, so the schema already documents claims splitting, the html/text format default, the 256 KB document cap, and the optional label. The description adds only the interpretive detail that matching is literal across words, figures, dates, and named items, which is useful but not parameter-specific, so the baseline 3 stands.

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?

It states a specific verb and resource (submit privacy claims plus the privacy policy or supporting document) and specifies the output shape: each claim tagged as supported, contradicted, or never mentioned, with quoted sentences. What is missing is differentiation from the many lookalike siblings such as wever_terms-evidence-check, wever_claim-evidence-check, and wever_data-evidence-check; an agent must infer from the word 'privacy' which rail applies.

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 tool is for checking claims against a privacy policy, and the description says it matches words, figures, dates, and named items but does not interpret meaning. There is no explicit 'use this when... instead of X' routing against the dozen other evidence-check siblings, so selection depends on the agent's own inference.

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