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

With no annotations, the description carries full transparency burden. It discloses the computation method (CBN check digit from bank code plus first nine digits), the scope (tests against every bank code), typical result size (~30 to ~3), and limitations (checksum validity only, no account existence check, no name lookup). This goes beyond the schema and gives a clear behavioral model.

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 the core purpose in the first sentence. Each subsequent sentence adds value: mechanism, typical output, and limitations. No fluff or redundancy. It is compact yet information-dense, ideal for an agent parsing it quickly.

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?

The description conveys the primary output (shortlist of possible banks) and key limitations, but no output schema exists, so the description must cover return behavior. It does not explicitly describe the output shape when an optional bank_code is provided (whether it returns a single bank, boolean, or different format). This is a minor gap given the tool's moderate complexity, but the overall coverage is strong.

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%, with clear descriptions for 'account' and 'bank_code.' The description does not add significant semantic details beyond restating that the account is 10-digit and that testing happens against bank codes. It adds minor context about the shortlist behavior but doesn't enhance the parameter definitions meaningfully. 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?

Clearly states the tool's function: 'Work out which Nigerian banks a 10-digit NUBAN account number could belong to.' This distinguishes it from siblings like list_banks and lookup_bank, which focus on bank metadata rather than account resolution. The description also clarifies what it does not do (confirm account existence, return account holder name), further sharpening purpose.

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?

Provides explicit usage context: 'narrows a shortlist without contacting any bank' explains when to use it. It also gives exclusions: 'does NOT confirm the account exists' and 'never returns the account holder's name, which requires a licensed NIBSS account-name enquiry,' steering users to alternatives when needed. The optional bank_code parameter is explained via the schema and reinforced in the description.

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