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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, yet the description adds substantial behavior: NPI/Vendor ID matches are IDENTIFICATIONS while name matches are CANDIDATE leads only (no DOB on the list), currently_excluded is a derived flag that is null with status_unknown:true when undeterminable, and the dataset covers everyone EVER excluded, not just current exclusions. These are non-obvious traits an agent needs and none are recoverable from annotations or schema.

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 core question and resource are front-loaded and every sentence carries information, but the parenthetical enumeration of eight sibling state tools and the LEIE cross-reference make it longer than strictly needed for routing.

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 correctly carries the return-value burden, describing what every match carries (published action, reason code/label, debarring department/agency, derived currently_excluded flag). For a keyless, read-only screening tool with full schema coverage, nothing an agent needs to invoke it correctly 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 baseline is 3, but the description adds real semantic weight beyond the schema: it explains the identification-vs-candidate distinction for npi/vendor_id vs name and the reason (no date of birth to disambiguate same-named providers). It slightly under-explains limit, but the parameter meaning is materially enriched.

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?

Opens with a specific question ('Is this healthcare provider debarred, suspended, or disqualified from the New Jersey Medicaid program?') and names the exact verb+resource (screens name/NPI/Vendor ID against the NJ Treasury Ineligible Provider List). It explicitly distinguishes itself from the federal LEIE pack and names each sibling state tool, so an agent can route without opening any schema.

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/credentialing screening for a NJ Medicaid provider) and names the alternatives (the leie pack for federal, the NY/CA/TX/FL/PA/GA/OH state siblings). It also gives the actionable rule 'Pass npi or vendor_id to turn a name lead into an identification,' which is explicit when-to-use guidance.

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