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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds information they cannot express: no wallet or payment is required, no arguments are needed, and — critically — the output is a sample rather than live screening data, which prevents an agent from mistaking it for real OFAC results.

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?

Two short sentences, zero filler, with the cost/purpose signal ('[FREE]', 'before paying') front-loaded so the agent grasps the value proposition immediately.

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 zero-parameter, read-only preview with no output schema and full annotation coverage, the description supplies everything needed to invoke it correctly and interpret the result as illustrative data. It could be marginally stronger by stating what the real screening response contains, but nothing required for correct invocation 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?

The tool takes zero parameters (schema coverage 100%, empty object), so the baseline is 4. The description reinforces this with 'no arguments needed', aligning with the empty schema rather than contradicting it.

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 exactly what the tool returns (a sample response for sanctions_screen) and frames it as a preview of the paid counterpart, which cleanly separates it from the many *_preview siblings. An agent can tell from the description alone that this is a free shape-inspection call, not real screening data.

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?

Gives a clear use condition: run it to see the response shape before paying 0.006 USDC for sanctions_screen. The paid alternative is named, so the when-to-use decision is easy to infer, though it never explicitly states 'use sanctions_screen instead when you need actual screening results'.

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