Search the self-hosted HHS OIG LEIE by individual or business name, with optional two-letter state and a bounded result limit. Returns evidence IDs for follow-up. Name similarity alone does not establish identity.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Individual or business name, at least 2 characters. | |
| limit | No | Maximum rows, default 10 and maximum 50. | |
| state | No | Optional two-letter US state code. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds a critical behavioral caveat: 'Name similarity alone does not establish identity,' warning that results are potential matches, not confirmations. It also specifies that the tool returns 'evidence IDs for follow-up,' setting expectations for output structure.
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?
The description is three concise sentences: the first states the operation and inputs, the second states the output, and the third is a crucial caveat. No wasted words; key information is front-loaded.
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 simple read-only search tool with full schema coverage and safety annotations, the description covers the main inputs, output shape (evidence IDs), and a vital caveat about identity. It could also note data recency or that it is a self-hosted snapshot, but this is not critical for calling the tool correctly. Lacking an output schema, the description sufficiently bridges the gap.
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%, with detailed descriptions for each parameter (name min length, limit default/max, state format). The description adds no new semantic details beyond restating that state is 'optional two-letter' and the limit is 'bounded'. Baseline 3 is appropriate given complete schema coverage.
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 uses the verb 'Search' with a specific resource ('self-hosted HHS OIG LEIE') and outlines the inputs (name, optional state, limit) and output ('evidence IDs'). It clearly indicates a name-based search tool but does not explicitly differentiate itself from sibling tools like leie_lookup_npi or leie_exclusion_details.
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 implies usage for searching the LEIE by name but does not explicitly state when to use it over alternatives. It mentions 'individual or business name' and 'follow-up', but names no alternatives such as leie_lookup_npi for NPI searches. No explicit when-not-to-use guidance exists, so an agent must infer usage from the tool's purpose.
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.