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

With no annotations provided, the description carries the full behavioral burden and does so: it discloses the fixed role set, round bounds, that outputs include evidence lineage, peer challenges, belief changes, falsifiers and a Detective Basic audit, and critically that calling the tool returns a REST/x402 checkout contract without executing the product or charging. That mutation/payment boundary is exactly the kind of disclosure an agent needs.

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 and front-loaded: mechanism first, exclusions next, then the return-set enumeration and the payment/checkout caveat last. Long sentences, but nearly every clause adds a constraint or output fact, so little is wasted.

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 no-output-schema, no-annotation tool of this complexity, the description enumerates the return fields and states the execution/payment boundary, which is unusually complete. The remaining gap is the undocumented job_id and evidence-identifier semantics, which the description leaves entirely to the schema.

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 0% across 5 parameters, so the description must compensate and only partly does. It clarifies that context and evidence are caller-supplied (with evidence presumably bounded) and that rounds are 1-3, but job_id is never explained and evidence item/id semantics are left to the schema.

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 (compares competing interpretations/paths) and pins the mechanism precisely: four fixed named roles (Operator, Skeptic, Buyer, Adversary), 1-3 bounded rounds, over caller-supplied question/context/evidence only. An agent can distinguish this from siblings like evidence_judge or detective_basic 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?

Gives strong boundary conditions: only caller-supplied evidence, no outside retrieval, no action execution, no treating peer statements as evidence or majority agreement as truth. However it never explicitly routes the agent versus alternatives such as evidence_judge or when a single-role audit (detective_basic) is the better choice, so it stops just short of full when/when-not guidance.

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