Argus

Overview Schema Source Related Servers Discussions Admin

Test User Action

test_action

Destructive

Click target and return before/after changes, observation and optional expectation checks. Examples: {"text_present":"Saved"}, {"count":{"label":"tasks","delta":1}}. Unknown is not pass; a mismatch is a lead, not a confirmed bug.

Instructions

Tool call template

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": {
      "target": "<target>"
    },
    "name": "test_action"
  }
}

Input Schema

Name	Required	Description	Default
`expect`	No
`target`	Yes
`expectation`	No
`double_click`	No
`accept_dialog`	No

Output Schema

Name	Required	Description	Default
`data`	No
`run_id`	Yes
`stages`	No
`status`	Yes
`recovery`	No
`operation`	Yes
`error_code`	Yes
`session_state`	Yes
`schema_version`	No
`progress_omitted`	No
`progress_delivery_failed`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.12.0Oct 28, 2026
- addedInput schema / properties / accept_dialog
```
Added value: +{
+  "default": false,
+  "type": "boolean"
+}
```
- addedInput schema / properties / double_click
```
Added value: +{
+  "default": false,
+  "type": "boolean"
+}
```
Changed4 schema fields changedv0.10.0Oct 26, 2026
- removedInput schema / properties / expect / title
```
Removed value: -"Expect"
```
- removedInput schema / properties / expectation / title
```
Removed value: -"Expectation"
```
- removedInput schema / properties / target / title
```
Removed value: -"Target"
```
- removedInput schema / title
```
Removed value: -"test_actionArguments"
```
Changed12 schema fields changedOct 26, 2026
- removedOutput schema / properties / data / title
```
Removed value: -"Data"
```
- removedOutput schema / properties / error_code / title
```
Removed value: -"Error Code"
```
- removedOutput schema / properties / operation / title
```
Removed value: -"Operation"
```
- removedOutput schema / properties / progress_delivery_failed / title
```
Removed value: -"Progress Delivery Failed"
```
- removedOutput schema / properties / progress_omitted / title
```
Removed value: -"Progress Omitted"
```
- removedOutput schema / properties / recovery / title
```
Removed value: -"Recovery"
```
- removedOutput schema / properties / run_id / title
```
Removed value: -"Run Id"
```
- removedOutput schema / properties / schema_version / title
```
Removed value: -"Schema Version"
```
- removedOutput schema / properties / session_state / title
```
Removed value: -"Session State"
```
- removedOutput schema / properties / stages / title
```
Removed value: -"Stages"
```
- removedOutput schema / properties / status / title
```
Removed value: -"Status"
```
- removedOutput schema / title
```
Removed value: -"AgentResult"
```
Addedv0.5.2Oct 26, 2026
Removedv0.5.1Jul 21, 2026
First observedv0.4.0Apr 27, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare destructive/openWorld/non-idempotent, so safety is covered. The description adds valuable behavioral context beyond that: it returns before/after changes and an observation, and it explains that an 'unknown' result is not a pass and a mismatch is only a lead—non-obvious semantics that shape correct interpretation.

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

Conciseness4/5

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

Front-loaded with the core action and return behavior, then examples, then caveats. Dense but nearly every clause carries useful information; the terse 'work as in click_what' phrasing assumes sibling familiarity but is efficient.

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?

An output schema exists so return shape needn't be spelled out, and the description covers assertion semantics well. But for a destructive, open-world action with 5 params at 0% schema coverage, the unexplained 'expectation' parameter and the missing note on preconditions make it only adequately complete.

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 coverage is 0%, so the description must compensate. It does well for the object 'expect' param via concrete examples and for double_click/accept_dialog by reference, but the separate 'expectation' string parameter is never explained or distinguished from 'expect', leaving a real ambiguity the schema does not resolve.

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?

States a specific verb (click) and resource (target) and adds that it returns before/after changes plus observations. It references the sibling click_what for related behavior, which helps position it, though the name 'test_action' is itself generic and requires the description to carry the meaning.

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?

It tells the agent double_click and accept_dialog 'work as in click_what' and gives a rule of thumb ('a mismatch is a lead, not a confirmed bug'), implying this is for assertion-style clicks. However, it never states explicitly when to choose this over click_what, leaving the selection boundary to inference.

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