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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, and the description adds real context beyond that: it names the rule sources (capability catalog, sanctioned-jurisdiction and app-prohibited category rules) and enumerates the five possible verdicts plus the accompanying payload. It doesn't disclose data freshness, coverage limits, or what happens when inputs are omitted (all 7 params are optional), which keeps it short of a 5.

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?

Three dense sentences, front-loaded with the purpose and ending with the negative scope, with no filler. Slight redundancy in re-explaining return values that the output schema already documents.

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 the verdict enumeration is technically duplicative, but the exclusions and rule sources are genuinely necessary context for a compliance-adjacent screening tool. The main missing piece is guidance on what happens with the zero required parameters and how the optional booleans/markets affect the verdict.

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 7 parameters, so the description must carry the load: it does map five of them (registration country, target markets, category, volume band, processing history) to the screening logic. But previous_account_closed_by_provider is never mentioned, and the format expectations for registration_country (ISO-2 uppercase) and target_markets are left entirely to the schema. Partial compensation, so a baseline-adjacent 3.

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 ("Quick qualitative screen of whether a business can apply to PayFresco") plus the exact input dimensions driving the verdict. The closing sentence enumerates what it does NOT do, which cleanly separates it from start_application, application_handoff, and assess_payment_setup.

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?

Frames the tool as a pre-application, pre-quote screen and explicitly excludes approval, approval-odds estimation, fee quoting, submission, and outreach, which implicitly routes the agent to the application/assessment siblings. It never names those siblings directly, so the agent must infer the handoff point rather than being told it.

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