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

Beyond the annotations (readOnly, openWorld, idempotent), the description discloses valuable behavioral details: 'The 10-digit NPI format is validated before any API call' and 'Reports partial success... well-formed NPIs with no registry record land in notFound, while NPIs whose lookup hit an upstream error land in errored — kept distinct from confirmed misses.' This adds error-handling context not present in the annotations, with no contradictions.

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 detailed but well-structured: it leads with the core purpose, then lists the returned data, and concludes with validation and error behavior. Each sentence serves a purpose, though the enumeration of output fields could be considered redundant if the output schema already documents them. It is appropriately 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 tool with a single parameter, full schema coverage, and annotations covering read-only/open-world/idempotent, the description is remarkably complete. It explains what it does, when to use it, how it validates input, and how it handles partial success—covering all operational aspects an agent needs. The output schema exists, so field-level details are not 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?

The input schema has 100% coverage for the single parameter: it describes the type (string or array), pattern (10 digits), and maxItems (10). The description repeats these facts ('up to 10 per call', 'validated before any API call') without adding new meaning. Since schema coverage is complete, the baseline of 3 applies.

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 clearly states the tool fetches the complete NPPES record for one or more NPIs (up to 10 per call), listing specific output fields like taxonomy, addresses, and credential. It differentiates itself from siblings by focusing on complete records by NPI, though it does not explicitly name alternatives.

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 provides clear context: 'Decodes an NPI from a claim, prescription, or another health data source' tells the agent when to use this tool—when you have an NPI and want a full provider profile. However, it does not explicitly state when not to use it or mention sibling tools (npi_lookup_taxonomy, npi_search_providers) as alternatives, so it lacks exclusions.

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