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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds substantive behavior: no network request, fetch, money movement, message, sharing, configuration change or external write; a paid 0.10 USDC call on Base via x402 exact with 10 signed-wallet free calls per rolling 30 days; and a wallet-proof header that must be bound to the exact JSON arguments and route. It also states the return carries an Ed25519 signed receipt, which is not derivable from annotations or schema.

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 and the sibling distinction are front-loaded, and every sentence carries information (verdicts, read-only scope, price, auth binding, contract links). It is a single dense block that mixes purpose, billing and provenance, so structure could be improved with separation, but there is little dead wording.

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 deeply nested schema with no output schema, the description covers what to submit, what the report contains, the possible verdict labels, and the payment/auth requirements. An agent has everything needed to decide to call it and to assemble valid arguments.

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 much is already documented, yet the description adds real meaning by describing the intended content of the nested objects: triggers, what is stopped, in-flight/queued/scheduled dispositions, restart paths and who may restart, component capabilities, and tests with what they observed. That frames the semantics of the 'observed' field and the enum choices beyond the bare schema text.

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: submit a kill-switch design and receive a signed report on whether the switch actually halts the system. It enumerates the inputs (what fires it, what it stops, in-flight/queued/scheduled handling, restart paths and who can restart) and the verdict labels (label_not_control, halt_unproven, halts), and explicitly separates itself from the sibling wever_incident-plan-check.

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 names the nearest alternative (wever_incident-plan-check) so an agent can route incident-plan material elsewhere, and it scopes usage by stating that only the material in the call is read. It does not give an explicit 'use this when / don't use this when' rule for the other dozens of agent-readiness checks, so the routing guidance is clear but not exhaustive.

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