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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds the caveat 'Informational only — not a recommendation or referral,' which clarifies that the output is editorial and not personalized advice. It also mentions language support (EN/ES), adding value beyond the structured annotations.

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 a single, well-structured sentence that front-loads the purpose, lists the key output components, and includes a crucial disclaimer without redundancy. Every clause earns its place, making it concise and immediately informative.

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 an informational tool with three well-documented parameters and no output schema, the description adequately covers what the tool returns (quick answer, requirements, institutions), optional state filtering, language options, and its non-recommendation nature. It is sufficiently complete for the agent to know when and how to use it.

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?

The input schema covers all three parameters with descriptions, including enums for loan_type and lang. The description adds minor semantic context like 'optionally state-filtered' and implies loan_type relevance, but this does not significantly exceed the schema's own documentation. Given 100% coverage, a baseline score of 3 is appropriate.

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 answers 'can I get a(n) X with an ITIN?' and specifies the output: editorial quick answer, typical requirements, and institutions with documented ITIN programs. It distinguishes from sibling tools like find_itin_lenders (which focuses on lenders) by emphasizing the direct answer and informational nature.

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?

The context is clear: it's for getting an informational answer, optionally filtered by state and language. It explicitly notes it's not a recommendation or referral, but it does not name alternative tools or state when NOT to use it. Since it's one of several ITIN tools, explicit exclusions would improve distinction, but the current description offers sufficient context for usage.

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