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

Goes well beyond the annotations: it discloses the payment model (0.10 USDC per call on Base via x402 exact, 10 signed-wallet free calls per rolling 30 days), the required X-Wever-Wallet-Proof binding to the exact JSON arguments and route, the enumerated verdicts (audit_blind, log_gaps, log_unverified, audit_ready), and that the report carries an Ed25519 signed receipt. It also confirms the read-only profile in concrete terms (no network request, fetch, money movement, message or external write), consistent with readOnlyHint=true.

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?

Front-loaded with the core purpose and the sibling routing, and most sentences carry real information (pricing, auth binding, verdicts, contract link). However, it is a very dense block of run-on clauses enumerating every field twice, which slows parsing and buries the verdict enum mid-paragraph.

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 carries the return-value burden and does: it describes the signed, field-by-field report, what gaps it names (missing principal or timestamp, shared actors, authorizations not on file, design not followed by the sample), and the verdict set. For a nested-object tool with optional inputs, an agent has enough to call it correctly on the first attempt.

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 75%, so the baseline is 3, and the description adds meaning by explaining what each design flag and each entry field is actually evaluated against — actor, principal, authorization, inputs, outputs, timestamp — and that 'authorizations' is the set of grants, mandates and approvals on file. It omits the optional 'label' parameter and the maxItems bounds (1000 entries, 100 authorizations), which the schema carries.

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?

States a specific verb and resource up front: 'submit an agent's logging design, a sample of its log, or both', and the output it produces ('The signed report says field by field what the design promises and what the entries hold'). It explicitly names the neighboring tools (wever_actor-attribution-check, wever_approval-record-check, wever_audit-evidence-check) and the narrower question each answers, so an agent can route without opening the schema.

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?

Gives explicit when-to-use-this-vs-siblings routing: per-run actor attribution belongs to wever_actor-attribution-check, approval record validity to wever_approval-record-check, counterparty SOC 2/ISO evidence to wever_audit-evidence-check. It also states the scope boundary ('Reads only the material in the call') and that either design, entries, or both may be supplied.

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