validate_us_routing_numbers

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

With no annotations, the description carries the full disclosure burden and does it well: metered cost of up to one credit per distinct number, a required user-approval gate, distinct-vs-total number counting, and the critical caveat that results are source observations rather than proof of account existence or ACH eligibility. It also flags a retry hazard on failure.

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?

Front-loads purpose, then cost, then caveats in descending order of importance. Multiple short lines, each carrying a distinct constraint; the only borderline line is the 'not the free web preview' note, which earns its place as disambiguation but would be stronger if it named the sibling.

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?

No annotations and no output schema, so the description must cover safety, cost, and result interpretation — it covers all three, including what the response is and is not evidence for. An agent has enough to decide whether to call, what to confirm first, and how to report results.

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 0%, so the description must compensate and largely does: it defines the 1–10 cardinality of routing_numbers, the per-distinct-number credit cost, and the exact gating semantics of confirm_api_credits=True. It does not specify the string format (9 digits) or behavior when the flag is false.

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 with batch bounds: 'Check 1–10 US routing numbers against the existing metered registry API.' It implicitly separates itself from the free-preview sibling ('This is not the free web preview') but never names the sibling it is not, so an agent must infer the routing to lookup_us_routing_number.

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 real conditions: requires a qualifying API key/plan, get user approval for credit spend before setting confirm_api_credits=True, and do not auto-retry a failed call. It stops short of explicitly naming the free alternative or stating when a plain lookup is preferable.

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