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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description focuses on what they cannot: data freshness ('refreshed daily from the official sources'), the shape of results (possible matches with a score plus the listing), and the commercial model ('Paid per call from your Stratum API balance, or use a test key'). Cost-per-call and test-key fallback are genuinely useful operational context not encoded anywhere else.

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 tightly packed sentences: capability and sources first, then return shape, then billing. No filler, no restatement of the title, and the least obvious fact (per-call cost) is held to the end where it is still visible.

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 no output schema, the description responsibly states what comes back (scored matches plus the listing, and every list screened with its date). Billing and freshness are covered. Minor gap: no mention of what a no-match response looks like or how scores should be thresholded, which matters for a screening tool.

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 100%, so every parameter (name, type, dateOfBirth, nationality) is already documented with examples and formats. The description only restates that the subject can be a person or organisation, adding no format, default, or edge-case guidance beyond the schema.

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?

Specific verb ('Screen') plus a precisely bounded resource (a person or organisation against UK, UN, EU and US OFAC lists). The named sources and daily refresh make it unmistakably distinct from sibling tools like sanctions_lists (which likely enumerates lists) and screen_export_controls (a different screening regime).

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 is implied: you screen a person or organisation when you need to check them against sanctions lists, and the 'type' semantics are echoed ('person or organisation'). But it never states when to prefer this over screen_export_controls or sanctions_lists, nor any prerequisites such as key/balance requirements for first-time callers.

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