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

Annotations declare readOnlyHint=false and idempotentHint=false, so a write that is not idempotent is expected. The description adds real value by disclosing the short-lived ES256 receipt, binding to request/action hashes, the signing-key prerequisite, and the 'not authorization' caveat. However it says little about retries, resubmission semantics, or what happens when signing key is absent beyond 'receipt unavailable.'

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 description buries the tool's function under referral to a sibling, then devolves into a long free-trial/marketing paragraph about agent_output_verification, HTTP alternatives, pricing, and payment instructions that have nothing to do with calling decision_check. The result is bloated and off-topic for the task at hand.

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 10-parameter tool with 10% schema coverage and no nested-object warnings, the description should clarify the meaning and requirements of parameters. Instead, a large fraction of the text is trial/pricing content irrelevant to the tool, while critical behavioral details (idempotency handling, receipt lifetime, key-missing behavior) are only glossed.

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 10%, so the description carries most of the burden, yet it only lists the seven required argument names without explaining semantics. It does supply one detailed example payload, which helps agents infer nested shapes, but leaves the meaning of risk_tier, claims, and evidence largely to the raw schema.

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 pivots around 'Run pre_action_check and attach a short-lived ES256 readiness receipt,' which conflates this tool with a sibling's behavior rather than stating its own distinct purpose. It never cleanly says decision_check produces a Gate result plus a signed receipt distinct from pre_action_check. The name/mechanism is inferable, but the core verb+resource framing is muddied by leading with the sibling tool call.

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 a clear ordering rule: require decision_verify to return gate_passed before using the result in an enforcement path, and it explicitly disclaims authorization. This frames when the result is valid for enforcement, though it doesn't contrast decision_check against pre_action_check directly.

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