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

The annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavioral context beyond them: it operates only on saved checks with no store fetch, scan, or login, and it is advisory because ARC stops before payment. It also documents the error envelope shape ({error:{code, message, next_step}}), which annotations do not provide.

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 description is front-loaded with the trigger condition, then the return contract, then the scope constraint and error shape. Every sentence carries distinct information: when to call, what comes back, what it does not do, and how errors surface. Dense but with zero filler.

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?

There is no output schema, so the description must carry the return contract, and it does: it enumerates why, fix (including the 'not recorded' sentinel), next_step, and links, plus the error format. For a one-parameter read-only lookup with a named upstream trigger, nothing an agent needs in order to call it correctly 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?

There is a single parameter with 100% schema coverage, so the schema already defines `store` as a domain or URL. The description adds marginal value with a concrete invocation example that shows the accepted shape ("gymshark.com") and the response keys it drives. This is a modest lift above the schema baseline rather than substantive new parameter semantics.

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 states a specific verb-plus-resource: it returns the reason a store is blocking checkout plus the recorded fix, along with next_step and record links. It is clearly differentiated from siblings by naming before_checkout as the upstream trigger and by stating 'Saved checks only: no store fetch, no scan, no login.' An agent can tell this apart from can_agent_checkout or precheck without opening any 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?

The trigger conditions are explicit: call after before_checkout reports reaches_checkout is false, or when an agent is stuck at a store and wants the reason and fix. That names one concrete alternative and the condition that selects this tool. It stops short of a full when-not statement (e.g., what to call instead if you want a fresh readiness check), so it falls just below the top band.

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