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

readOnlyHint=true is already declared, and 'without moving money' reinforces that no funds are transferred. The valuable addition beyond annotations is the cost and entitlement model: 5 prepaid credits and a production billing requirement, which an agent needs before invoking. It stops short of describing the computed output or failure conditions.

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?

Two short sentences with the core computation front-loaded and the billing constraint immediately after. There is no filler or redundant restatement 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?

With no output schema, the description should indicate what comes back (a delta, a variance, a flagged boolean), and it does not. Units and input constraints for the two required integer parameters are also unaddressed, leaving meaningful gaps for a numeric calculation tool.

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 0%, so the description must carry the burden, and it only loosely maps to the two parameters by naming 'expected versus paid amount'. It never states that values are integers in cents, whether negative differences are meaningful, or whether the two must be comparable currencies.

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 and object: calculate expected versus paid amount for an invoice. Combined with the name 'invoice_reconciliation', an agent knows this returns a comparison rather than performing a payment. It does not differentiate from any sibling, but no sibling in the list plausibly overlaps with invoice reconciliation.

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?

'without moving money' implies when this is appropriate (analysis rather than payment execution), and 'PAID ONLY: 5 prepaid credits; production billing required' gives a concrete access precondition. There is no explicit when-not guidance or named alternative, so usage is implied rather than spelled out.

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