Compass by 402rates

Execute a synthetic test action

execute_test_action

Execute the selected case's action: synthetic order, retry attempt, page retrieval or result submission. Identical keys and input replay the stored outcome. Calls, effects and simulated credits remain observable. No real payment.

Input Schema

TableJSON Schema

Name	Required	Description
`cursor`	No	Partial-result page cursor: first or second.
`run_id`	No	Run identifier from start_agent_test.
`task_id`	No	Task identifier bound to this run.
`quantity`	No	Synthetic quantity. The task specifies one unit.
`action_key`	No	Caller-generated UUID. Identical key and payload identify the same synthetic operation.
`record_ids`	No	Synthetic record identifiers submitted by the caller, at most six.
`action_type`	No	Case action: attempt, get_page or submit_result. Not accepted by the original case.
`access_token`	No	Secret short-lived run token. Omitted from reports. MCP client history may retain this argument.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 10, 2026

addedInput schema / properties / action_type

Added value: +{
+  "description": "Case action: attempt, get_page or submit_result. Not accepted by the original case.",
+  "maxLength": 24,
+  "type": "string"
+}

addedInput schema / properties / cursor

Added value: +{
+  "description": "Partial-result page cursor: first or second.",
+  "maxLength": 16,
+  "type": "string"
+}

addedInput schema / properties / record_ids

Added value: +{
+  "description": "Synthetic record identifiers submitted by the caller, at most six.",
+  "items": {
+    "maxLength": 64,
+    "type": "string"
+  },
+  "maxItems": 6,
+  "type": "array"
+}

First observedSep 9, 2026

TDQS

A3.7/5.0

Behavior4/5

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

The description adds meaningful behavioral traits beyond the sparse annotations (readOnlyHint false, destructiveHint false): deterministic replay ('Identical keys and inputs replay the output'), observability ('Calls, effects and simulated credits remain observable'), and safety ('No real payment'). The annotations don't convey any of this, so the description carries the behavioral disclosure burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler. The first sentence conveys the exact purpose, the second covers replay and side-effect visibility, and closes with 'No real payment.' It is front-loaded and every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 8 optional parameters and no output schema, the description gives a solid high-level model and important behavioral traits. But it never explains how a case becomes 'selected' or refers to the dependencies (run_id/task_id from start_agent_test), and it does not describe the expected outcome object. The schema covers all parameters, but the sequencing preconditions are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, which raises the baseline to 3. The description does not add new parameter meaning beyond the schema: it repeats the action_key replay rule already described in the schema ('Identical key and payload identify the same synthetic operation'). It does not clarify the relationship between run_id, task_id, and the 'selected case' concept.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Execute') and a resource ('selected case's action') and enumerates concrete action types: synthetic order, retry attempt, page retrieval, result submission. It also disambiguates via 'No real payment' and 'synthetic', distinguishing this from real-payment tools. However, 'selected case' is not further defined, and it does not explicitly name a sibling for comparison, so a 4 is appropriate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: to execute the selected case's synthetic action types. The 'No real payment' note is a negative hint, but there is no explicit decision rule, no mention of alternatives (e.g., 'use test_payment for real payments'), and no prerequisite like 'use after start_agent_test'. It provides context but leaves selection to inference.

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

All Compass by 402rates tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?