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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description still adds real context beyond them: it discloses the call cost ("Costs 1 call") and that the plan data is only a summary (counts, states, years, as_of dates) rather than the full list, which prevents an agent from misusing the result.

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 tight sentences: what it returns first, then when to use it, then the alternative. Zero filler and nothing buried.

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?

A one-parameter read tool with full annotations and an output schema; the description covers purpose, output shape at a high level, cost, and the sibling boundary. Nothing an agent needs to call it correctly is 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?

Schema description coverage is 100% — the single `npi` parameter is fully documented in-schema as a 10-digit string with an example. The description adds no format or edge-case detail beyond that, so the baseline 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?

States a specific verb+resource (identity lookup of a US healthcare provider by NPI) and enumerates what comes back: name, credential, specialties, practice locations, groups, plus ACA/MA plan summary counts, states, plan years and as_of dates. It also explicitly distinguishes the resource from the sibling that returns the raw plan list.

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 an explicit use case ("confirm who an NPI is before checking networks") and an explicit hand-off ("For the plan list itself use plans_for_provider"), naming the alternative and the condition that selects it. No inference required.

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