Split a bill: tip amount, total and per-person share. Pure CPU, instant.
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"bill": "<bill>"
},
"name": "tip"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| bill | Yes | Bill amount | |
| people | No | Number of people | |
| percent | No | Tip percent |
Changes observed during successful MCP inspections.
Input schema / properties / billAdded value: +{
+ "description": "Bill amount",
+ "type": "number"
+}Input schema / properties / peopleAdded value: +{
+ "description": "Number of people",
+ "type": "integer"
+}Input schema / properties / percentAdded value: +{
+ "description": "Tip percent",
+ "type": "number"
+}Input schema / requiredAdded value: +[
+ "bill"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations supplied, the description carries the full behavioral burden. 'Pure CPU, instant' usefully signals a deterministic, side-effect-free, low-latency computation, which is meaningful context beyond a parameter listing. It stops short of confirming read-only behavior or describing what the response contains, which matters more here because there is no output schema.
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 operation front-loaded and no filler. The phrase 'tip amount, total and per-person share' slightly blurs outputs with inputs, but the brevity is appropriate for a simple calculator.
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 three-parameter calculator with no output schema and no annotations, the description covers the operation and the performance profile but leaves gaps: output shape is only loosely implied, and the behavior for omitted optional parameters (people, percent) is unstated. Adequate but not complete.
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 100%, so each of bill, people, and percent is already documented in the schema, making 3 the baseline. The description gestures at the percent and per-person concepts but adds no defaults (e.g., what happens if people or percent is omitted) or constraints beyond the schema text.
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 names a specific operation and resource: splitting a bill and computing tip amount, total, and per-person share. An agent can tell this is a bill-splitting calculator rather than a generic math tool. It does not, however, distinguish itself from the sibling tip_calculator, leaving a real ambiguity given the near-identical name.
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?
There is no explicit when-to-use guidance and no mention of alternatives, despite a sibling (tip_calculator) that appears to serve the same purpose. Usage is only implied by the phrase 'split a bill'. An agent has no stated basis for choosing between tip and tip_calculator.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.