Get Bill History

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds interpretive context beyond that: status enum semantics (PENDING/SUCCESS/FAILED) that directly enable the 'did my payment go through' use case, the type enum, and field meanings such as customer (phone/meter/smartcard) and token (electricity prepaid meter). The pagination envelope (page, totalPages) is disclosed too, though the 'recent' window and pagination mechanics are left undefined.

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 first sentence states purpose, the second gives usage context, and the commented JSON block documents the output in one structured pass — appropriate since no output schema accompanies this tool. The three examples are distinct (list, status check, specific query) and earn their place, though the overall definition is on the longer side.

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 zero-parameter, read-only tool with comprehensive annotations, this is nearly complete: the only thing the schema and annotations can't convey — return structure — is documented inline with field-level comments. The remaining gaps are minor: 'recent' is not time-bounded, and page size/pagination behavior is not described.

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 tool takes zero parameters, so the baseline is 4 and the description correctly avoids manufacturing parameter documentation. It instead documents the return payload thoroughly and offers client-side filtering guidance ('filter by type=UTILITYBILLS'), which is the closest thing to parameter semantics this tool has.

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 specific verb and resource — 'Returns the user's recent bill payment history' — and names the full category scope (airtime, data, electricity, cable TV). This explicit scope distinguishes it from sibling tools like monei_get_transaction_history (all transactions) and monei_pay_bill (initiating a payment), so an agent can route correctly without opening schemas.

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?

A dedicated paragraph states 'Use this when the user wants to review past bill payments, check if a payment went through, or audit utility spending,' which is clear, contextual guidance. Three concrete intent-to-action examples ('Did my electricity payment go through?', 'When did I last buy MTN airtime?') reinforce when to call it. However, no exclusions or explicitly named alternative tools are given, so it falls just short of a 5.

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