Evidence package for a vendor SLA breach (PAID $1.00)

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

The description adds two facts not in the annotations: the operation costs $1.00 and is settled via x402/base/USDC on eip155:8453 through a remote POST. Since annotations already declare non-read-only, open-world, non-idempotent and non-destructive behavior, this payment/cost disclosure is the meaningful residual gap-filler. It is consistent with readOnlyHint=false (a paid remote call that produces new evidence).

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?

It is short and front-loaded, but the first clause merely restates the title verbatim and no further explanation is given. The route/price line is the only content that earns its place beyond the title.

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?

An output schema exists so return values need not be described, but for a paid, open-world tool with three parameters at 0% schema coverage and a required nested object, the description leaves the agent unable to construct a valid, correctly-scoped call or understand what the evidence package covers.

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 three parameters, and the description supplies zero parameter meaning. The required `url` (what is fetched? the vendor endpoint?), the nested `claimed_sla` object, and `window_hours` (default 168) are entirely undocumented anywhere. Nothing compensates for the coverage gap.

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?

"Evidence package for a vendor SLA breach" names a specific output resource, but the verb is implied (generate? assemble? verify?) and nothing distinguishes it from evidence-producing siblings such as v1_audit_evidence_package, v1_bestex_evidence, or v1_finance_attested_evidence. An agent knows the topic area but not precisely what operation is performed or on what input.

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, when-not-to-use, or alternative guidance at all. The only signals are the payment route and price. The agent must infer that this applies when it holds an SLA claim against a vendor, and gets no help choosing among the many evidence siblings.

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