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

With no annotations, the description carries the full burden. It discloses that it returns no PHI, that NPI is public data, and that it currently only resolves one physician, returning a not-found response for others. This is transparent about limitations and privacy. It doesn't explicitly state it's read-only, but that's implied and not a significant gap. A 4 is appropriate because it covers behavioral traits well without over-claiming.

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?

Two sentences, no filler. The first sentence states the core purpose, the second provides usage context and behavioral notes. It's front-loaded and every word earns its place. Ideal conciseness.

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 simple one-parameter lookup with full schema coverage, the description covers purpose, usage context, limitations, and privacy. It doesn't specify the exact return format for credentials, but that's not necessary for correct invocation, and no output schema is present. It's complete enough for an agent to call it safely and understand likely outcomes.

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% – the parameter description fully explains the NPI format and constraints. The description adds no new semantic info about the parameter beyond repeating '10-digit' which is already in the schema. Per guidelines, baseline is 3 when coverage is high, so a 3 is correct.

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 function: given an NPI, check if it matches a SickSlip physician and return credentials. It specifies the resource (SickSlip physician) and verb (check and return). It is distinct from sibling tools which deal with pricing, tiers, availability, and note verification, so no ambiguity.

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?

It explicitly states when to use: when an AI assistant has an NPI from a PDF, verification context, or user-provided string and wants to confirm ownership. It also discloses a crucial limitation – currently only resolves Dr. Kawalek's NPI and returns a not-found for others – which tells the agent when the tool will fail. This is strong usage guidance, even though it doesn't mention alternatives since siblings are unrelated.

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