Drive real devices from your AI Coding tool. Embed a client SDK (Unity, Godot, Flutter, iOS/macOS, Android, React Native, Web) in your app, then capture screenshots, traverse the UI tree, inject taps and key events, and run automated test tasks on the physical device over a secure relay.
Scored across 6 tools
Each tool has a distinct purpose: list_devices for enumeration, device_status for connectivity, device_ping for latency, device_detail for tokens/connect info, list_tasks for task discovery, and run_task for execution. No overlap or ambiguity.
Naming follows a predictable pattern with prefixes like list_, device_, and run_. The only minor deviation is device_detail not being a verb, but the pattern is consistent enough to be easily understood.
Six tools is well-scoped for a debug relay server: device management, status checks, task discovery, and execution. Each tool earns its place without redundancy or bloat.
The surface covers the full lifecycle: device discovery, connectivity checks, latency measurement, detailed info retrieval, task manifest listing, and task execution. No obvious gaps for the stated purpose.
Full info for one device, including its clientToken and a ready-to-paste Unity connect snippet. Only call this when the user explicitly asks for the token or connect instructions.
| Name | Required | Description | Default |
|---|---|---|---|
| device | Yes | device name or sid from list_devices |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry behavioral context. It discloses the specific outputs (clientToken, Unity connect snippet) and implies the operation is read-only by calling it 'info.' It also hints at cost/restriction by saying 'only call when explicitly asks,' which is useful behavioral context. While it doesn't explicitly state safety (read-only), the word 'info' and the nature of the tool make it clear enough.
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?
Two sentences, no fluff. The first sentence front-loads the core purpose and outputs; the second gives the usage condition. Every word earns its place.
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 single-parameter tool with no output schema, the description provides enough: it names the output fields (clientToken, Unity snippet) and gives a clear usage condition. It does not mention potential errors or rate limits, but these are not critical for such a simple tool. The description is sufficient for an agent to decide when to call and what to expect.
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%: the parameter 'device' is described as 'device name or sid from list_devices.' The description does not add any extra meaning about the parameter beyond what the schema already provides. This is a baseline 3 because the schema handles the semantics fully.
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 ('Full info for one device') with a clear resource, and distinguishes from siblings by noting it returns clientToken and a Unity connect snippet. This is unique among device_ping, device_status, and list_devices, so the agent knows exactly what this tool offers.
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?
Explicitly says 'Only call this when the user explicitly asks for the token or connect instructions.' This provides a clear when-to-use condition and implicitly tells when not to use it (for routine status or ping checks). It effectively routes the agent to the right sibling without naming them explicitly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Round-trip ping to the connected device; measures relay + device latency.
| Name | Required | Description | Default |
|---|---|---|---|
| device | No | target device: name or sid from list_devices. Omit only when the account has exactly one device. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry behavioral disclosure. It states the behavior (ping, measures latency) which implies a read-only diagnostic. However, it does not explicitly state non-destructiveness, timeouts, or failure modes. The description is adequate but not comprehensive for a tool without annotation support.
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?
A single, front-loaded sentence with zero fluff. It efficiently communicates the tool's purpose without any unnecessary details.
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 simple tool with one optional parameter and no output schema, the description conveys the core purpose and the schema covers the parameter. The mention of 'measures relay + device latency' implies the return value. The only missing aspect is explicit usage guidance, but that falls under a different dimension.
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?
The schema already provides a 100% descriptive coverage of the single parameter, including how to specify the device and when to omit it. The description adds no extra parameter meaning, so the baseline of 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 clearly states the action (round-trip ping), the target (connected device), and the measured metric (relay + device latency). It distinguishes this from siblings like device_detail and device_status, which are about details/status, while ping is a connectivity/latency check.
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?
No explicit guidance on when to use this tool versus alternatives. It does not mention conditions like 'use for connectivity checks' or 'prefer device_status for state information'. The only hint is the parameter description about omitting the device when there is a single device, but no strategic usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check whether the target device is connected to the relay.
| Name | Required | Description | Default |
|---|---|---|---|
| device | No | target device: name or sid from list_devices. Omit only when the account has exactly one device. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not mention side effects, read-only behavior, or potential impact. While a status check is likely non-destructive, the description leaves this implicit rather than explicit.
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?
The description is a single, concise sentence that directly conveys the tool's purpose without unnecessary detail or repetition.
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 description is adequate for a simple status check, but it does not indicate what the response will contain or how the result is expressed (e.g., boolean, status string). Given the lack of an output schema, a bit more context about the return value would improve completeness.
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?
The schema fully covers the single optional 'device' parameter with a clear explanation. Since schema coverage is 100%, the baseline applies and the description adds appropriate context about the parameter's meaning.
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 clearly states the tool's purpose: checking whether a target device is connected to the relay. It uses a specific verb and resource ('device', 'relay'), though it does not explicitly distinguish itself from sibling tools like device_ping or device_detail.
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?
There is no guidance on when to use this tool compared to alternatives such as device_ping or device_detail. The description implies a status check but does not clarify which scenario should use this tool versus sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the device token pairs this connection can drive (name, sid, region, online). Call this FIRST; when several devices exist, ask the user which one to use and pass its name or sid as the "device" argument on subsequent tool calls. Tokens are NOT included — use device_detail when the user asks for connect instructions.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the full burden. It discloses that tokens are NOT included, which is a key behavioral constraint, and implies a read-only listing by describing returned fields (name, sid, region, online). It does not mention side effects, but for a zero-parameter list tool this is sufficient; the disclosure of token omission adds real value beyond the empty schema.
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 with no waste: the first states the action and output fields, the second gives the workflow guidance, and the third clarifies a crucial exclusion and points to the sibling. Every sentence earns its place, and the main purpose is front-loaded.
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 zero-parameter tool with no output schema, the description fully covers what the agent needs: the return fields, the token omission, the 'call first' directive, and how to use the result on subsequent calls. There is no gap that would prevent correct invocation or interpretation.
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?
The tool has zero parameters, so there is nothing to explain. Baseline for zero params is 4, and the description correctly avoids inventing parameters, instead focusing on the output and usage workflow.
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 and resource: 'List the device token pairs this connection can drive' with fields name, sid, region, online. Differentiates from siblings by explicitly saying tokens are not included and directing to device_detail for connect instructions, so the agent can tell it apart without opening schemas.
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?
Explicitly instructs to call this FIRST, tells the agent to ask the user which device and pass its name or sid as the 'device' argument on subsequent calls. Also explicitly names device_detail as the alternative when connect instructions are needed, leaving no ambiguity about when to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Discover what the connected device client can do: returns its task manifest (task types with descriptions and payload schemas) as reported by the device build. Call this before run_task when unsure which task types exist.
| Name | Required | Description | Default |
|---|---|---|---|
| device | No | target device: name or sid from list_devices. Omit only when the account has exactly one device. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It says 'returns' and 'discover', implying a read-only operation, but doesn't explicitly state safety, latency, or any potential side effects. The phrase 'as reported by the device build' hints at a remote query but omits details like authentication requirements or failure modes.
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?
Two sentences, front-loaded with purpose and usage. Every word earns its place—no filler, and the critical call-before-run_task advice is placed at the end for emphasis.
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 simple discovery tool with one optional parameter and no output schema, the description covers what it returns, when to use it, and why. It could mention potential errors or the format of the manifest in more detail, but it's adequate for an agent to call it correctly.
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%: the 'device' parameter is fully described in the schema ('name or sid from list_devices. Omit only when the account has exactly one device.'). The description adds no additional parameter context, so it meets the baseline but adds no value.
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 ('Discover', 'returns') and resource ('task manifest'), and explicitly distinguishes its role from run_task by describing it as a discovery step. The purpose is unambiguous and distinct from siblings like list_devices and run_task.
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 explicit when-to-use guidance: 'Call this before run_task when unsure which task types exist.' This tells the agent the exact trigger condition and references the relevant sibling, making the decision tree clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send a task to the connected device over the debug relay and wait synchronously for its result.
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | task type the device client understands, e.g. "echo" | |
| device | No | target device: name or sid from list_devices. Omit only when the account has exactly one device. | |
| payload | No | task payload object | |
| timeout_ms | No | how long to wait for the device (default 60000, max 120000) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full responsibility. It discloses that the tool waits synchronously for a result, which is a key behavioral trait. However, it does not mention potential side effects, failure modes, or whether the operation is destructive, leaving some ambiguity.
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?
The description is a single, well-structured sentence that front-loads the primary action and follows with the waiting behavior. It is concise with no unnecessary words or repetition.
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?
Given the lack of an output schema, the description adequately covers the tool's purpose and parameters. It explains the synchronous wait but does not describe the result format or error handling, which would be useful but are not critical for a basic understanding.
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?
All four parameters have descriptions with meaningful details: 'type' includes an example, 'device' explains how to reference it, 'payload' is identified as an object, and 'timeout_ms' specifies default and maximum values. The only minor gap is the vague 'task payload object' description, but overall coverage is strong.
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 clearly states the tool's function: sending a task to a connected device over the debug relay and waiting synchronously for the result. It uses a specific verb ('Send') and resource ('task') and is distinct from sibling tools like device_ping or list_tasks.
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 description implies when to use the tool (whenever a task needs to be executed on a device), but it does not explicitly mention alternatives or conditions for choosing this over other tools. No clear 'instead of' or 'when not to use' guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
device_detaildevice_pingdevice_statuslist_deviceslist_tasksrun_taskControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
Drive real Android & iOS devices and web browsers from natural language for mobile + web QA. 290+ tools across device control, app management, automation sessions, browser automation, and flow recording / replay. Bearer-auth — get a token at robotactions.com → Profile → API Tokens.
Disposable cloud Android emulators for coding agents: run an APK or PR build, tap, type, screenshot.
Cloud iOS simulators and Android emulators your agent can create, drive, and throw away.
Add one secure layer between your agents and this server.
