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

With no annotations, the description carries the full burden and does so: per-call credit costs (3 credits for Ghana, 1 for signals-only, 0 for unresolved provider error), the privacy guarantee that the registered name is never returned or stored, and the failure mode (unresolved on provider error). This is unusually rich behavioral context.

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?

Line-broken and front-loaded: purpose first, then per-region behavior and costs. Dense but every line carries operational information; only minor tightening would be possible given the amount of region-specific behavior it must convey.

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 annotations or output schema for a complex, credit-charging identity check, the description covers verdicts, costs, privacy, and geography well. It stops short of explaining how identifier parameters (phone vs account_number vs bank) combine to form the lookup, which is the remaining gap.

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% across 8 parameters, so the description must compensate. It clarifies that 'name' is the person's given name to be matched and that 'country' takes an ISO code (GH, KE...), but leaves bank, email, phone, network, account_number, and mask_registered_name entirely undocumented—only 'network' is touched indirectly via the free signals list.

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: does the given name match the name registered on a mobile money wallet or bank account. It also scopes geography (Ghana live, other regions degraded) and names the exact verdicts returned, distinguishing it clearly from validate_phone/validate_contacts siblings.

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?

Explicit when-to-use ('only use with the person's consent, at sign-up'), conditional behavior elsewhere in Africa/USA, and downstream action rules ('on partial, confirm with the user; on mismatch, do not pay out'). An agent knows both the prerequisite and how to act on each outcome.

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