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

Beyond the readOnly and non-destructive annotations, it explains the registry pre-check, the prefilled personal link, the on-site completion and e-signature step, the typical timeline, and the fact that nothing is filed until the person signs. It also adds a privacy constraint not to collect SSN or date of birth in chat.

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 front-loaded with recognizable user phrases and then moves into the workflow. It is somewhat long and includes marketing-style timing details, but nearly every sentence contributes operational context.

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?

With no output schema, the description still explains what the tool returns: a personal link to the prefilled free form. It covers the full handoff, what happens after the person finishes, expected delivery timing, and the key privacy boundary.

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%, so the schema already explains all six fields. The description adds useful workflow context such as prefilling known fields and not collecting SSN/DOB, but it does not add per-parameter meaning beyond what the schema provides.

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 action and resource: starting an NPI application for an individual professional. It clearly distinguishes itself from registry-checking siblings by describing a handoff to a prefilled SimpleNPI form rather than a lookup or verification.

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 provides abundant concrete trigger phrases such as 'get me an NPI number' and 'Type 1 NPI', plus a partial exclusion: it first checks the registry to avoid duplicate applications. However, it does not explicitly name sibling alternatives like lookup_npi or verify_npi for already-issued NPIs.

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