postTestExceptionsUpload exception logs for a specific test (by test ID) rather than by session ID. The result reads the test's exceptions back to confirm they were stored. The automation dashboard may not show exceptions uploaded this way after the test ended.
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | The exceptions to attach: {"exception": ["first message", "second message"]} | |
| testId | Yes | The test ID |
Changes observed during successful MCP inspections.
Input schema / properties / data / additionalPropertiesPrevious value: -trueNew value: +falseInput schema / properties / data / descriptionPrevious value: -"Exception payload to upload"New value: +"The exceptions to attach: {\"exception\": [\"first message\", \"second message\"]}"Input schema / properties / data / propertiesAdded value: +{
+ "exception": {
+ "description": "Exception messages, one string each",
+ "items": {
+ "type": "string"
+ },
+ "minItems": 1,
+ "type": "array"
+ }
+}Input schema / properties / data / requiredAdded value: +[
+ "exception"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description only needs to add behavior beyond that — and it does, disclosing that the call reads the exceptions back as a storage confirmation and that dashboard visibility may be unreliable post-test. It does not cover idempotency, overwrite semantics, or auth requirements.
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?
Three sentences, front-loaded with the action and the distinguishing scope, followed by verification behavior and the one operational caveat. No sentence is redundant or padded.
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 two-parameter mutation with annotations covering safety and a fully documented nested schema, the definition supplies the distinguishing scope, the read-back behavior, and the post-test visibility caveat. The read-back partially compensates for the absence of an output schema, though the exact response shape remains unspecified.
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 100% and the nested data object, its required 'exception' array, and item constraints are fully documented in the schema. The description only restates that identification is by test ID, adding no syntax or format detail beyond the structured fields. 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?
States a specific verb+resource (upload exception logs) with an explicit scope qualifier ('for a specific test (by test ID) rather than by session ID'). This directly distinguishes it from the sibling postSessionExceptions without needing to open either schema.
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?
Gives a clear selection rule against the session-based alternative and a caveat about when the result may be misleading ('automation dashboard may not show exceptions uploaded this way after the test ended'). It does not name the sibling tool explicitly or state prerequisites such as whether the test must already exist.
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.