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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantial behavioral context: name matches are candidate leads only because the list lacks DOB, while NPI/license matches are identifications; the dataset covers everyone ever excluded and currently_excluded is derived from reinstatement. This is meaningful disclosure beyond what structured fields provide.

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-loaded with the central question and mostly dense and information-rich. It is long and repeats the identification-vs-candidate-lead distinction twice (once in prose, once in the closing sentence), which is slight redundancy but not padding.

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 and does so: match reason text, currently_excluded flag, and the ever-excluded scope are all explained. An agent has everything needed to call it and interpret results.

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 baseline is 3, but the description adds epistemic weight per identifier type — NPI/license turn a name lead into an identification — and notes name matching works across word order. This is useful semantics layered on top of the schema rather than mere repetition.

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 specific verb (screens) and resource (Texas HHSC OIG Medicaid Provider Exclusions Database) and frames the core question it answers. It explicitly positions itself against named siblings (leie pack, ny_omig_check_exclusion, ca_medical_check_exclusion), so an agent can distinguish it without opening the 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?

Gives concrete when-to-use scenarios (pre-payment/credentialing screening, 'is this provider excluded from Texas Medicaid', checking an NPI) and names the alternative jurisdictions/tools. Nothing about when to reach for this versus the New York or California counterparts 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.