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

While annotations already carry destructiveHint=true and readOnlyHint=false, the description adds the concrete consequence: it resets reconciliation state, telling the agent exactly what gets mutated. 'No payment or bank verification occurs' discloses the absence of external side effects. This complements the annotations without contradicting them.

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?

A single 21-word sentence is front-loaded with the prerequisite ('After confirmation'), followed by the action, then the negative scope. Every clause earns its place and there is zero boilerplate or repetition of the title.

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 state-changing 6-param tool with zero schema descriptions, the description covers the core flow: when (after confirmation), what (record evidence, reset reconciliation), and what not (no payment/bank verification). However, it omits the optimistic-concurrency semantics of expected_version and the roles of confirmation_token and idempotency_key, which matter for a destructive write. Since an output schema exists, the lack of return-value detail is acceptable.

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?

With 0% schema description coverage, the description carries the parameter-documentation burden but only hints at `data` (receipt evidence) and the confirmation gate. Critical params like expected_version (a 64-char hex, indicating optimistic locking), idempotency_key, and confirmation_token are entirely unexplained. The schema field titles do most of the work that the description should have done.

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 states a specific verb-resource pair ('record receipt evidence') and adds the state effect ('reset reconciliation'), making the operation concrete. The negative clause ('no payment or bank verification occurs') actively distinguishes it from siblings like sparkclose.reconcile_funding. An agent can tell what this tool does and what it deliberately does not do.

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?

The opening 'After confirmation' states the prerequisite condition for invoking the tool, which is useful timing guidance. The exclusion clause clarifies that this tool is not for payment or bank verification, implicitly routing those cases to siblings like sparkclose.reconcile_funding. No alternative tool is explicitly named, so the guidance is clear but slightly indirect.

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