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

Annotations already mark it read-only, idempotent, open-world, and non-destructive. The description adds significant behavioral context beyond that: it is 'Offline and free', it returns specific states (no_change, verify_first, stop, invalid_new_account) plus call-back steps for a human, and crucially, it 'never says an account is safe, and never claims who owns it.' This clarifies limits on what the tool does not guarantee, which is essential for a financial validation tool and goes well beyond the annotation flags.

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 tightly written. It front-loads the scenario and purpose, follows with a summary of actions and outputs, then adds two short, high-value sentences on cost/availability and limitations. Every sentence contributes; there is no fluff or repetition of schema content. The structure guides the reader from context to behavior to constraints efficiently.

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 tool with three params and no output schema, the description is complete. It explains what the tool does, the exact return values, the call-back steps that remain human tasks, that it is offline/free, and its non-claims about safety and ownership. This is enough for an agent to decide when to call it and to interpret a result. The absence of an output schema is compensated by listing the possible return strings.

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 documents each parameter with examples (e.g., IBAN format, 'Leave it out for a first registration'). The tool description reiterates the comparison behavior ('compares it with the account on file') and how supplierCountry is used, but it adds no new syntactic or semantic detail beyond the schema. It does clarify the role of each param in the overall logic, but the schema descriptions already cover this. Baseline 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 opens with a concrete scenario ('A supplier says their bank details changed') and a clear verb-resource pair ('check the request before the vendor record is touched'). It then details specific actions (validate IBAN, compare with account on file, flag country mismatches) and names the four possible return values. This distinguishes it from the sibling verify_iban, which would only validate structure, whereas this tool adds comparison and flagging logic.

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 clearly states when to use the tool: when a supplier reports a bank detail change and before any vendor record is modified. It also gives param-level guidance (e.g., 'Leave it out for a first registration') and notes the limitation that it never claims ownership or safety. However, it does not explicitly contrast with alternatives like verify_iban, so the 'when not to use' is inferred rather than stated.

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