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

With no annotations provided, the description carries the full behavioral burden and does well: it details data sources, row contents, source links and read times, error handling (marked, never guessed), state license coverage, human review for unresolved licenses, email delivery, and free first check. It does not cover authentication, rate limits, or what happens after the free check, but for a data-gathering tool this is a rich disclosure that adds substantial value beyond the 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 description is a single dense paragraph, front-loaded with the core action and then enumerating many details. It is informative but runs long and could be more structured with bullet points or shorter sentences for readability. Some details, like the list of states, are necessary but contribute to the density.

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?

The tool has a complex data-gathering scope, six parameters with only 50% schema coverage, and no output schema or annotations. The description does a thorough job explaining what data is returned, how discrepancies are handled, state restrictions, and delivery method. It is nearly complete, but gaps remain around the undocumented parameters (company, ref_code, contact_time) and post-check behavior.

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 50% (three of six parameters have no schema descriptions). The description compensates by explaining the NPI list limit (500) and fallback to name search, and it mentions email delivery. However, parameters like company, ref_code, and contact_time are not addressed in the description, leaving half the inputs undocumented. It adds meaningful context for the primary inputs but does not fully close the coverage gap.

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 opens with a specific verb and resource: 'Send a list of NPIs (up to 500) for a provider enrollment check.' This distinguishes it clearly from sibling tools like vendor_check_request and provider_check_status, which handle different entities or status retrieval. An agent can immediately tell what the tool does and what it operates on.

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?

Usage is implied by the description: send NPIs for a check. However, there is no explicit guidance on when to use this tool versus alternatives like vendor_check_request or provider_check_status, nor any prerequisites or exclusions. The sibling names suggest related workflows, but the description does not route the agent between them.

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