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

With no annotations at all, the description carries the full burden and does well: it discloses a paid call ($0.02 USDC on Solana, one payload per payment), the non-destructive guarantee (never signed, never stored), which checks run, and that findings are individually named. Gaps remain: no failure/error behavior (e.g. what happens on a malformed or non-conforming artefact) and no statement about latency or response size.

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?

Two dense sentences with no filler; the single-payload and no-sign/no-store constraints are stated up front. Slight deduction: the price leads the sentence, so the actual action is slightly back-loaded, and phrases like 'domain both-ways agreement' are compressed to the point of ambiguity.

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 one-parameter tool with no annotations and no output schema, the description covers cost, safety profile, check set and finding granularity, which is most of what an agent needs. Missing pieces are the failure path and any pointer to the referenced 'published policy table' the checks are run against.

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 3 is the floor, but the description adds real meaning: exactly one artefact per call ('the one unsigned EVM (EIP-712) payload you submit'), the required descriptor form, and the memory-only handling of that object. It does not explain what makes an artefact valid at the transport level, but it reinforces the schema description rather than repeating it.

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 concrete verb+resource: a signed pre-flight lint of one unsigned EVM (EIP-712) payload, and enumerates the checks (domain both-ways agreement, amount, descriptor-form vs published policy table). The explicit 'EVM (EIP-712)' qualifier separates it from the sibling payload_preflight_svm. It stops short of 5 because 'pre-flight lint' is internal jargon and the description never names the criteria/precheck siblings it coordinates with.

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?

Usage context is only implied: the 'unsigned payload before signing' framing lets an agent infer when to call, and the EVM label implies the SVM split. There is no explicit when-to-use/when-not, no statement of what to run first (payload_preflight_criteria, payload_preflight_precheck) and no guidance on what a caller should do with the findings.

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