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

Beyond the annotations it discloses payment terms (0.10 USDC per call on Base via x402 exact, shared 10 signed-wallet free calls per rolling 30 days), the auth requirement (bind X-Wever-Wallet-Proof to the exact JSON arguments and tool route), and that the response carries an Ed25519 signed receipt. It also confirms the safety profile in prose ('no network request, fetch, money movement, message, sharing, configuration change or external write'), which is consistent with readOnlyHint and destructiveHint=false. This is substantial context the structured fields do not 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?

The content is largely useful, but it is delivered as very long comma-spliced sentences, including a sprawling enumeration of every report finding and a comma list of verdicts, which makes it hard to scan. The operational facts (endpoint, price, auth, receipt) are all present but appended at the end rather than front-loaded. Some of the failure-condition enumeration could be compressed or left to the contract page.

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 carries the return-value burden and does so: it explains what the signed report contains, the possible verdicts (remembered_without_consent, consent_gaps, consent_unverified, principal_in_control) and what the findings mean. Combined with endpoint, pricing, auth binding and the contract/human page links, an agent has everything needed to call this correctly and interpret the result.

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 67%, and the prose largely restates what the schema already says about consent.asked, consent.form, the controls fields and kept categories, sometimes with the same wording as the enum descriptions. It adds a little meaning by framing the agreements as 'how agreement is given' and controls as 'see, correct and switch off', but it gives no guidance on partial or ambiguous inputs, defaults for the empty required list, or what happens when kept categories exceed covers. Marginal value over the schema, so the baseline band applies.

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 names a concrete action (submit a memory setup) and the question the check answers ('whether the principal agreed and stays in control'), which is specific enough to act on. It also distinguishes itself from three siblings explicitly (scope-check, context-sharing-check, deletion-check), so an agent can route without opening the schema. It loses a point because the core purpose is buried inside a long opening sentence that leads with input enumeration rather than with what the tool does.

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 gives clear routing rules: what the system keeps is wever_memory-scope-check, whether one sharing event needs consent is wever_context-sharing-check, whether removal clears memory everywhere is wever_memory-deletion-check. That is real when-to-use-this-vs-alternative guidance rather than implied usage. It does not state explicit exclusions or prerequisites for calling (e.g. when a consent question is out of scope entirely), so it falls short of the top band.

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