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`	Yes	Run identifier from start_agent_test.
`task_id`	Yes	Task identifier bound to this run.
`quantity`	No	Synthetic quantity. The task specifies one unit.
`action_key`	Yes	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`	Yes	Secret short-lived run token. Omitted from reports. MCP client history may retain this argument.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 24, 2026

addedInput schema / required

Added value: +[
+  "run_id",
+  "task_id",
+  "action_key",
+  "access_token"
+]

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

A4/5.0

Behavior5/5

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

Beyond the annotations, the description discloses idempotent replay on identical keys/input, observability of calls/effects/simulated credits, and the absence of real payment. These are precisely the behavioral details an agent needs before invoking a synthetic execution tool. There is no contradiction with the annotations.

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?

Three short sentences, front-loaded with the verb and action-kind list, with each sentence adding distinct operational information: scope, replay behavior, observability, and no-payment guarantee. There is no filler or redundancy.

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?

The schema plus description is adequate for understanding parameters and general behavior, but there is no output schema and the description omits the expected response shape and sequencing prerequisites, such as when a selected case is ready to execute after start_agent_test. For an 8-parameter execution tool, this leaves the agent to infer post-call behavior.

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

Parameters4/5

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

Schema descriptions already cover all 8 parameters, so the baseline is 3. The description adds operation-level meaning by explaining that identical keys and input replay stored outcomes and by restating action_type values in plain language. It does not add per-parameter details beyond that, so it does not reach 5.

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 identifies a concrete operation, 'Execute the selected case's action', and enumerates the supported action kinds: synthetic order, retry attempt, page retrieval, or result submission. This is specific enough to separate it from sibling list/read/inspect/start tools, though it does not explicitly name a sibling alternative.

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 wording implies the tool is for synthetic execution after a case has been selected/started, and 'No real payment' signals a boundary against real-payment flows. However, it never explicitly tells an agent when to use this tool instead of inspect_test_state, read_agent_test_report, or test_payment.

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

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?