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

Annotations already cover readOnly, idempotent, and non-destructive safety. The description adds beyond that: 24-hour cache (freshness), verified source (NPPES NPI Registry/CMS), US-only scope, and a concise summary of returned fields (name, credential type, taxonomy, address, status). This is meaningful operational context that annotations alone do not provide. No contradiction with annotations.

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 logically ordered: purpose, safety/geographic constraints, parameter details, return summary, usage guidance, source/cache, and feedback fallback. Purpose is front-loaded. Some redundancy with annotations ('Read-only. No side effects. Idempotent.') and schema is present, but each section earns its place and the text remains focused.

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?

Complete for a single-parameter read-only tool with an output schema: it covers provenance (NPPES/CMS), data freshness (24-hour cache), return-value summary, sibling routing, and the agent-gap feedback contract. An agent has everything needed to select, invoke, and interpret this tool correctly.

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 description coverage is 100% and already documents '10-digit NPI number e.g. 1003000126. No dashes. Required.' The description mostly repeats this, adding only 'or spaces' to the formatting constraint. This is marginal added value, so a baseline 3 is appropriate — the schema carries the semantic weight.

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 and resource: 'Fetch NPI registration details for a US healthcare provider by NPI number.' Explicitly differentiates from the sibling compliance_search_npi_by_name by input type (exact NPI vs. provider name) and from other compliance fetch tools like compliance_fetch_finra_broker by the resource domain. An agent can immediately tell what this tool does and what it does not do.

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?

Provides clear when-to-use guidance: 'Use this when you have the exact 10-digit NPI.' Names the alternative explicitly: 'Use compliance_search_npi_by_name instead when you only have the provider name.' Also adds a geographic constraint (US only) and a fallback instruction (report_feedback) for when the result doesn't serve the user's need.

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