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

Annotations already declare readOnlyHint, idempotentHint, closed-world and non-destructive, so the safety profile is covered. The description goes further by disclosing the per-item outcome vocabulary (ready, missing, not answered, not applicable), that a copyable checklist comes back, and that post-application expectations (≈3-day approval, volume ramp, reserve, payouts, currencies) are included. It also explicitly guards against the most likely misreading — that readiness equals approval odds — which is real behavioral value 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?

One front-loaded paragraph with zero filler: the purpose comes first, then the returned states, then the expectations, then the non-capabilities. The requirement list is dense but every clause earns its place, and no sentence merely restates 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?

With annotations covering the safety profile and an output schema present, the description does not need to spell out return values, and it still sketches them enough to set expectations. For an 11-parameter diagnostic tool the remaining hole is the two enum parameters and notes, whose meaning rests entirely on terse field names. Overall an agent has what it needs to call this correctly.

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 11 parameters, so the description must carry the load, and it only partly does: the enumerated checklist items map to the boolean fields (registration documents, website with products and prices, refund policy, product description, volume estimate, processing statements, closure explanation). Nothing explains why business_category matters (several enum values look high-risk) or what processing_history buckets imply for the check, and the notes parameter is never mentioned.

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: a self-check of the documents and site requirements a business must have ready before applying to PayFresco, and it enumerates them (registration documents, live website with products and prices, refund policy, product description, volume estimate, processing statements, closure explanation). The closing negatives — does not approve, quote fees, submit an application, or contact anyone — carve it away from check_eligibility, start_application, and application_handoff, so an agent can place it without opening a 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?

Usage context is explicit: run it before applying, and it is a readiness check rather than an approval chance, a fee quote, or a submission. The exclusions on the tail make the when-not side clear. The gap is that it never names a sibling directly, so the very close build_readiness_checklist (and application_handoff for the next step) is left for the agent to infer.

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