Buy a Verification

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false) by disclosing exactly what is consumed (one verification credit at a stated price), what is refunded if no verdict is produced, that the tool itself never charges, and that completion happens out-of-band on a returned Stripe URL with anonymous claim instructions. That is precisely the context an agent needs to avoid calling it casually or expecting a synchronous result.

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?

Front-loads the action and the definition of the unit, then price, guarantee, return value, and scope requirement in order of usefulness. Slight redundancy between 'This tool does NOT charge anything itself' and 'payment happens on the returned URL', though the emphasis is defensible for a payment-adjacent tool.

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 one-optional-parameter tool with no output schema and sparse annotations, the description covers everything material: cost model, credit consumption, failure-to-charge behavior, return payload, anonymous claim path, and required auth scope. Nothing an agent needs in order to decide whether and how to call it is missing.

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 coverage is 100% and there is only one optional parameter, so the schema already documents callback_url fully. The description adds no meaning about how the redirect base URL interacts with the returned checkout URL, so baseline 3 applies.

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?

Uses a specific verb ('Purchase') and a precisely defined resource ('one verification — a causal verdict on whether a model switch holds quality on YOUR production traffic'), so an agent knows this is a paid, one-unit transaction rather than a read. It does not explicitly contrast itself with the verdict-reading sibling (metrx_get_verdicts), so the distinction relies on the verb and pricing language.

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?

Establishes clear preconditions for use: a 'write'-scoped API key, a $149/$99 cost, and the 'no verdict, no charge' guarantee that tells an agent the risk profile of the call. It stops short of naming when-not-to-use or a prerequisite step (e.g., checking balance first), so it lacks explicit exclusions.

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