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

Annotations already cover safety (readOnlyHint, openWorldHint), but the description adds genuinely non-obvious behavior: results are exact only up to 1,200, above which the response is the literal string '1200+' with a pointer elsewhere, and a single call accepts at most 5 specialties. That cap is the key operational constraint an agent needs before calling.

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?

Three short sentences, no filler, and the core question plus scope constraint is front-loaded ahead of the caveats. Every sentence contributes a distinct fact (what it counts, the 1,200 cap, the 5-specialty limit).

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?

There is no output schema, and the description does not say how results are shaped when multiple specialties are supplied (a map per specialty, or a single number), nor does it address the entity default. For a read-only counting tool the cap disclosure is strong, but these two gaps keep it at minimum viable.

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 only 25%, so the description must carry the load, and it covers specialty, state and ZIP-prefix narrowing plus the 'up to 5 specialties' limit. It says nothing about the `entity` enum, whose default is 'individual' — an agent could reasonably read 'how many providers' as all entities and silently get individual-only counts.

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 states a specific verb and resource — counting NPI Registry providers by specialty, optionally narrowed by state or ZIP prefix — and the 'how many' framing makes clear this returns counts, not records. It never names a sibling such as search_providers or lookup_npi, so differentiation is implicit rather than explicit.

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 only implied: the counting framing suggests it is the right tool when an agent needs an aggregate rather than a listing, and 'points to the full-list route' hints at an alternative once the count exceeds 1,200. No sibling tool is named and no explicit when-not-to-use condition is given.

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