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

Annotations already declare this as a non-readOnly, non-destructive, closed-world operation, but the description adds materially more: USDC payment with the exact amount taken from marketplace_services, escrow holding, and release timing ('when you accept the result, or 24 hours after a delivered, undisputed result'). It also discloses the auth prerequisite (agent_id + api_key, obtainable free and instantly at marketplace_register) and that x402 is currently disabled. That is real behavioral context beyond structured fields.

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 key routing information (shortcut vs marketplace_create_contract, verify_claims_smart alternative, escrow terms) is front-loaded and each sentence carries real information. There is some redundancy: the free/instant registration detail and the 'x402 is switched off' note appear both in the description and twice in the schema, which costs a bit of tightness.

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 paid mutation tool with no output schema, the definition covers payment mechanics, escrow release, credentials, and the alternative tools an agent might want. The remaining gap is what an agent receives after paying (result shape, how to retrieve it) and what happens on a dispute, though marketplace_get_result and marketplace_dispute_contract are visible siblings that imply those paths.

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 every parameter is already documented, including the disabled x_payment and the free/instant registration path for api_key and agent_id. The description largely restates those facts rather than adding semantics (e.g. it does not explain what task_payload shapes are valid for this specific listing or how deadline_hours interacts with escrow release). With the schema carrying the load, baseline 3 is appropriate.

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 establish what the tool does: it places the same order that marketplace_create_contract places, but pinned to this listing's service_id, and the sentence 'Order it with your agent_id and api_key' confirms it is a purchase action. The opening line ('Send an agent's result, its claims and, if you have it, the source text') describes the payload rather than the tool's action, which slightly muddies the read. Compared with the large sibling set of buy_* tools, it is clear enough to distinguish without opening the schema.

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 explicitly routes the agent in both directions: 'for any other listing use marketplace_create_contract' and 'For when you need the claims checked in depth, not just a receipt, use verify_claims_smart instead.' The paid-per-call fallback situation is also addressed ('x402 is switched off right now'), so there is no ambiguity about which tool or path to take.

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