Screen a provider/organization against the federal exclusion lists (HHS-OIG LEIE, and SAM.gov if configured). NPI match is exact; name match is flagged and identity-cautious. Returns sourced findings + a disclaimer. Facts, never an allegation.
| Name | Required | Description | Default |
|---|---|---|---|
| npi | No | ||
| name | No | ||
| state | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and excels: it discloses exact vs flagged matching, identity-cautious handling, return type (sourced findings + disclaimer), and a factual tone. No contradictions.
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 sentences, no redundancy, front-loaded with key action. Every phrase adds value. Perfect conciseness.
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?
Given no output schema and no annotations, the description explains purpose and matching but omits the 'state' parameter's role and output structure details. Adequate for a simple tool, but gaps remain.
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 0%, so the description must compensate. It explains the behavior of npi (exact match) and name (flagged), but does not mention the 'state' parameter at all. Partial coverage only.
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?
The description clearly states the action ('Screen a provider/organization'), specifies the target lists (HHS-OIG LEIE, SAM.gov), and explains matching types. It distinguishes from siblings like fda_enforcement and provider_lookup which have different scopes.
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?
The description does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or context. While the purpose is clear, the lack of when-not-to-use or sibling differentiation prevents a higher score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct function: FDA enforcements, new OIG exclusions, general provider lookup with exclusion flag, and detailed exclusion screening. No two tools have overlapping purposes.
All tools use snake_case and are descriptive, but patterns vary: fda_enforcement is a noun phrase, new_exclusions is adjective+noun, provider_lookup is noun+verb, screen_exclusion is verb+noun. This minor inconsistency slightly reduces clarity.
Four tools is appropriate for the healthcare provider risk domain, covering key areas without bloat. It's on the lower end but still sufficient for basic workflows.
Core functionality is covered (FDA recall alerts, new exclusions, provider lookup, exclusion screening). Missing a tool for detailed exclusion info or direct SAM.gov access, but the surface is reasonably complete for credentialing and procurement teams.