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

Annotations already declare readOnlyHint and openWorldHint, and the description adds useful context the annotations can't convey: the 50-row return cap, the 1,200-result count ceiling, and the CMS rejection of state-only queries. It doesn't mention the skip/limit pagination semantics, which it could have.

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 dense sentences, front-loaded with the searchable fields and followed by the constraint and the return behavior. The trailing marketing URL is the only element that doesn't serve the invocation decision.

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 10-parameter, no-output-schema tool, the description covers what's searchable, what's required, what comes back, and the result ceiling — enough to call it correctly. The unreachable gap is the entity/limit/skip semantics, which neither the schema nor the description explains.

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 only 30%, so the description has to carry weight. It does clarify specialty format (taxonomy description as the registry writes it), state (2 letters) and ZIP, but leaves entity, limit and skip entirely to the schema, which is sparse. Partial compensation only.

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 ('Search the live NPI Registry') and enumerates the searchable fields, so the agent knows exactly what matching surface it gets. It doesn't explicitly name the sibling tools (lookup_npi, validate_npi, count_by_specialty), but 'search' vs 'lookup'/'validate' is naturally distinguishable.

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?

Gives a concrete precondition — at least one of name, organization, specialty, city or ZIP — and explains why (CMS refuses a state-only query). It also points to an alternative for full lists beyond the 50-row window, though it never says when to prefer lookup_npi or validate_npi.

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