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

Annotations already carry readOnlyHint/openWorldHint/destructiveHint, so the bar is lower, but the description still adds real context: it states the call reads only supplied material with no network request or external write, discloses the 0.10 USDC x402 charge with 10 free signed-wallet calls per 30 days, and requires X-Wever-Wallet-Proof bound to the exact JSON arguments and route. The return is described as a report with an Ed25519 signed receipt. It stops short of explaining what happens on a failed payment or proof mismatch, which keeps it off a 5.

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?

Core purpose and payload are front-loaded in the first sentence, with output, safety, pricing, and auth requirements following in a sensible order. It is dense and slightly run-on, and the contract/human-page URLs are tacked on at the end, but no sentence is redundant given the payment and proof-binding requirements.

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 6-parameter nested-object tool with no output schema, the description covers the input shape, the verdict taxonomy, the failure findings the report names, the response artifact (signed receipt), and the payment/auth prerequisites. An agent has everything needed to construct a call and interpret the result without opening the contract page.

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?

With schema coverage at 67%, the description compensates by mapping fields to intent – kind/rule/deterministic/time for the trigger, approver/decision/actions-covered for approvals, investigation notes with trigger links, and action ids annotated with approval and investigation references. That linking semantics (a field holds an id pointing at another record type) is genuinely additive over the schema, though run, label, result, source and text remain unexplained.

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 opens with a specific verb ("submit") and resource ("one workflow run's records") and then enumerates exactly which record types belong in the payload: trigger/detection, investigations, approvals, actions. An agent can distinguish this from the many sibling checks (approval-chain-check, audit-evidence-check) because the scope is end-to-end run auditability, not a single evidence facet.

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?

The "Agent Readiness" prefix and the payload enumeration imply when the tool applies, and the verdict vocabulary (unprovable/gapped/auditable) clarifies the decision it supports. However, there is no explicit when-to-use or when-not-to-use statement and no sibling is named as the alternative for narrower checks, which matters given the large family of similarly named checkers.

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