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

Rich beyond the readOnlyHint annotation: discloses per-call cost ($0.05 via x402), the return shape (verdict, confidence, basis, reason), and the critical limitation that a match is a name match unless made on an identifier and is not an identity determination. This is exactly the behavioral context an agent needs.

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?

Four tightly packed sentences, front-loaded with the core action and sources, followed by cost, return values, and the crucial match caveat. No wasted words.

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?

Covers the two sources, per-call cost, return shape, and the name-vs-identifier matching distinction. For a read-only screening tool with a fully documented schema, nothing material 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?

Schema coverage is 100%, so the schema documents all six parameters thoroughly. The description adds meaningful value by clarifying the match-strength hierarchy (npi/uei/cage are strong identifiers vs. name matching), which informs how to weight the inputs, though it doesn't restate the individual formats.

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 (Screen) and resource (person or business) against two named, concrete data sources (LEIE and SAM.gov exclusions). The scope is unmistakable and clearly distinct from the sibling batch and sources tools.

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?

Implicitly positions this as the single-entity check in contrast to exclusion_batch_check, but never names the sibling or the condition (single vs. bulk) that selects it. The pricing note and the match-type disclaimer give useful framing, yet no explicit when-not-to-use guidance is offered.

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