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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description adds substantive behavior: server-side vs browser compute resolution, that inputs are processed transiently and not stored or logged, and that the output includes an AP2 artifact with execution_hash for chain provenance. That provenance-and-privacy detail is genuinely useful context an agent could not get from the annotations. It stops short of describing the shape or size of the crosswalk result, and the artifact-export behavior slightly complicates the read-only framing, though not to the point of contradiction.

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 content is badly ordered: the tool's actual function is the last clause, behind compute-mode mechanics, a Cloudflare hosting note, a privacy blurb, a chain-provenance note, a URL, and an FV-status receipt hash. Several sentences are platform boilerplate repeated across every node rather than tool-specific and could be lifted out entirely. Conciseness suffers from under-editing, not from excessive length per se.

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?

The description covers execution modes, privacy posture, and chaining, and points the agent at describe_tool for the output schema, which partially offsets the absence of a real output schema. What remains missing is the substance of the operation: what the crosswalk returns (a mapping table, a normalized code, a confidence value?) and what the four PSP enum values change about the result. For a mapping node with nested policy parameters, an agent still cannot predict the response.

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 100%, so the baseline is 3. The description's discussion of compute modes largely restates what the 'compute' parameter description already says, and it adds no domain meaning for the business inputs (psp, reason, network_code) — for example, what form a reason code takes or how network_code is keyed. It neither compensates for nor exploits the schema's coverage.

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 does state a specific verb and resource: 'Dispute reason-code crosswalk across PayPal, Stripe, Adyen and Square', with a spec identifier (PSP-DISPUTE-CROSSWALK-NODE-1). It is identifiable as a mapping/crosswalk tool rather than a validator or calculator. However, it never distinguishes itself from nearby siblings such as crosswalk_agent_payment_rail_trust or compute_paypal_response, and the actual purpose is buried at the very end after unrelated platform boilerplate.

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?

There is no when-to-use guidance and no named alternative. The only usage-like statement is the privacy constraint 'Use synthetic or anonymised inputs only' and the note that the node is 'static and credential-free', neither of which tells an agent when to pick this tool over the other crosswalk or PayPal-related tools. The reader must infer the trigger condition from the title alone.

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