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

Annotations already declare readOnlyHint, openWorldHint=false, and idempotentHint. The description adds value by specifying 'fully offline (bundled)', which aligns with openWorldHint=false, and by outlining the behavior of each mode (resolve turns plain-language into entries, get fetches exact code, browse walks hierarchy). It also notes the fallback from specialization to classification, which is a useful behavioral detail not in 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 two sentences, front-loaded with the core purpose and offline nature, then efficiently lists the three modes and their behavior. No wasted words; every clause contributes to understanding. The structure is logical and easy to parse.

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?

Given the existence of an output schema (which presumably describes return values), the description covers all necessary operational aspects: modes, filters, offline status, and the mapping to a sibling tool. It explains the hierarchy and fallback behavior, addressing likely agent questions about how to use the tool. No critical information appears missing for correct invocation.

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% with each parameter described. The description adds semantic context beyond the schema by explaining what each mode does and the hierarchy (grouping → classification → specialization), which enriches the understanding of mode and section/grouping parameters. It clarifies the mapping of resolved entries to provider search, which the schema does not convey. Thus it adds meaningful value beyond the structured definitions.

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's purpose: resolving and browsing the NUCC Healthcare Provider Taxonomy. It names the exact resource (NUCC taxonomy) and explains three distinct modes (resolve, get, browse) with concrete examples. It also differentiates from siblings by specifying that it covers the taxonomy code set NPPES uses, and explicitly maps its output to npi_search_providers.taxonomy_description, making its role distinct from provider retrieval tools.

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 implies when to use it: when you need taxonomy codes to populate npi_search_providers.taxonomy_description, or to browse the taxonomy hierarchy. It provides a direct mapping to a sibling tool, indicating a workflow. However, it does not explicitly list alternatives or state when not to use it (e.g., when you need provider records). Still, the context is clear enough for an agent to infer its role.

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