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

Goes well beyond the readOnly/idempotent annotations: it discloses this is a static check rather than a simulation, the exact category of findings returned, the $0.01 USDC x402 payment mechanics, that unpaid calls return PaymentRequired and retry via _meta["x402/payment"], that only a single-scoped authorisation is signed with no approvals, and that invalid input is rejected before charging.

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?

Dense but front-loaded, leading with the trigger and the inputs before the return values and payment mechanics. The payment sentences are long but each carries non-obvious operational information an agent needs to avoid failing on an unpaid call.

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 and a nested policy object, the description still explains the verdict vocabulary, what the findings cover, and the payment/error path. An agent has everything it needs to call this correctly without opening anything else.

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 100%, so the baseline is 3. The description adds real value the schema lacks: it explains that tx fields, typedData and untrusted text are alternative input modes and that the policy is optional, conveying the mutual-exclusivity structure a flat schema can't.

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: a pre-signature static check that takes tx fields, typedData or text and returns block/review/allow with decoded call and findings. It's clear apart from siblings, though it never names presign_demo or screen_text to carve out the boundary (the untrusted-text parameter overlaps notably with screen_text).

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?

'Call before your agent signs anything' gives a clear trigger, and it specifies which input mode to send (tx fields, typedData, or text) with an optional policy. It stops short of explicit when-not guidance or naming the sibling tools an agent should reach for instead.

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