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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses meaningful behavioral facts: funds are never touched, the receipt is independently verifiable, ALLOW does not guarantee execution, and this is only policy evaluation. This prevents a dangerous misreading of ALLOW as authorization. No contradiction with annotations.

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?

Three tight sentences front-load the most important information (call timing, result type, safety boundary) and every sentence earns its place. There is no fluff or repetition of schema content.

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?

Despite having no output schema, the description clearly states the return shape (signed preflight receipt, verdicts, reasons) and the side-effect profile. The tool's nested-object complexity is addressed by the schema, while the description supplies the critical temporal and trust context needed for correct use.

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?

The description adds a high-level mapping to policy constraints (max amount, allowed networks/assets, expected recipient, allowed origins), which helps the agent understand the policy object's intent. However, it does not document the action object, options, or references, so with 0% top-level description coverage it only partially carries the parameter-explanation burden; the schema's nested descriptions provide the remaining detail.

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 names a specific verb ('preflight'), a specific resource ('an autonomous payment' evaluated against policy), and the concrete result (signed receipt with ALLOW/REQUIRE_APPROVAL/BLOCK). It also distinguishes itself from actual payment authorization by explicitly stating the wallet/x402 client separately authorizes execution.

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 temporal trigger ('Call BEFORE an agent authorizes an autonomous payment') and a clear exclusion boundary ('Policy evaluation only: OCD never holds, moves, or authorizes funds'). It does not explicitly route to alternative sibling tools by name, so it falls just short of full guidance.

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