cancel_cost_approvalCancel an unused executable quote.
| Name | Required | Description | Default |
|---|---|---|---|
| approval_token | Yes | estimate_cost token. |
| Name | Required | Description | Default |
|---|---|---|---|
| code | No | ||
| canceled | No |
Changes observed during successful MCP inspections.
Output schema / additionalPropertiesRemoved value: -trueOutput schema / properties / canceled / descriptionRemoved value: -"True when the quote was canceled."Output schema / properties / code / descriptionRemoved value: -"Machine-readable outcome code."Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "properties": {
+ "canceled": {
+ "description": "True when the quote was canceled.",
+ "type": "boolean"
+ },
+ "code": {
+ "description": "Machine-readable outcome code.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered structurally. The description adds the useful precondition that only *unused* quotes can be cancelled, implying already-executed approvals are unaffected, but says nothing about irreversibility, error conditions, or token validity beyond that.
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?
One short sentence with no filler and the condition ('unused') front-loaded alongside the verb. Its brevity is efficient, though the same brevity contributes to the completeness gaps noted elsewhere.
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?
The tool is destructive but carries annotations and an output schema, so the safety and return-value burden is largely handled elsewhere. Still, an agent gets no guidance on when cancellation is permitted or what happens to the estimate afterwards, which matters for a destructive operation.
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% and the single parameter is fully described in the schema as an 'estimate_cost token'. The description adds no format, origin, or lifetime detail beyond what the schema provides, so the baseline 3 applies.
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 gives a verb ('Cancel') and an object ('an unused executable quote'), so the action is identifiable. However, the object wording ('quote') does not match the tool name ('cost approval'), leaving ambiguity about whether a quote and an approval are the same entity. There is no differentiation from siblings like estimate_cost or execute.
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 word 'unused' hints at a precondition, but there is no explicit statement of when to call this tool versus letting an approval expire or re-running estimate_cost, and no mention of alternatives. Guidance is essentially absent.
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.