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

Annotations cover safety (readOnlyHint, destructiveHint=false) and open-world scope, but the description adds substantial non-structured context: monthly OIG refresh with overwrite semantics, the fact that the LEIE contains only currently-active exclusions so reinstatement_date is effectively always empty, and an explicit name-collision caveat (common-name matches; agent/user must disambiguate via DOB/address/NPI). That is exactly the kind of trait annotations cannot express.

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?

Front-loads the definition and the when-to-use guidance, which is correct ordering. The statutory-code block is genuinely load-bearing for interpreting exclusion_type, but a few sentences are promotional or restate scope ('Pure-publisher posture', the oig.hhs.gov reminder, the repeated statement about active-only listings) and could be trimmed.

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 14-parameter tool with no output schema, the description covers source, freshness, legal meaning, scope limits, filter semantics, and the disambiguation caveat well. It stops short of describing the shape of a returned record (fields beyond the reinstatement_date note), which the absence of an output schema would otherwise require.

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 baseline is 3, but the description adds real semantic value the schema lacks: it enumerates the statutory exclusion codes (1128a1 through 1128b8) and their meanings, which is what exclusion_type filters on, and it clarifies that since/until are applied to the sort field and that results are limited to active exclusions. It still doesn't explain how the geographic/specialty filters interact or what a returned record contains.

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 precise verb+resource ('Returns entries on the HHS OIG List of Excluded Individuals/Entities (LEIE)') and immediately defines what the list means (barred from billing Medicare/Medicaid/federal healthcare programs). This clearly separates it from adjacent screening siblings like get_ofac_sdn and get_screening_list by naming the exact source and its legal consequence.

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 an explicit when-to-use list (healthcare-fraud exclusions, program-integrity research, geographic concentration, a specific person/business on LEIE), an explicit when-not ('not employment or eligibility decisions about individuals — Terms §8A'), and a cross-source pairing tip with get_federal_contracts. Nothing about routing is left to inference.

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