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

Adds substantial context beyond the annotations: match semantics (NPI/license = identification, name = candidate lead because there is no DOB or address), what fields come back (provider type, exclusion effective date), a disclosure that OMIG publishes no exclusion reason or statutory authority, and that the source is keyless. The annotations already cover read-only/idempotent safety, so this is well past the bar.

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 core question, then layers scope, match semantics, and output caveats in a logical order with no filler sentences. It runs long as a single dense paragraph and repeats the identification/candidate point twice, which costs it a point.

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?

With no output schema, the description carries the return-value burden itself and does so: provider type and exclusion effective date per match, plus an explicit statement that exclusion reason and statutory authority are absent and the response says so. An agent can call this correctly and interpret results without further information.

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% and the schema already explains all four parameters, including the NPI-as-identification and any-word-order name notes. The description reinforces the identification-vs-lead distinction but doesn't add syntax, formatting, or behavior for `limit` beyond what the schema states, so this sits at the baseline.

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?

Names a specific verb (screens/checks) and a specific resource (NY OMIG Medicaid exclusion list), and explicitly positions it against both the federal LEIE and the sibling ny_omig_exclusion_coverage. The opening question form removes any ambiguity about what calling it answers.

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?

States concrete use cases (pre-payment and credentialing screening for a NY Medicaid provider) and gives explicit routing logic: pass npi or license to upgrade a name lead to an identification. It also delineates the tool from the federal LEIE, so an agent knows which exclusion tool to pick.

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