Probe Android or iOS device debugger prerequisites and list matching running debuggable processes before attaching; does not initiate a debug session.
Probe optional platform debugger prerequisites and matching running debuggable processes; does not attach.
| Name | Required | Description | Default |
|---|---|---|---|
| appId | Yes | ||
| deviceId | Yes | ||
| platform | Yes | ||
| processId | No | ||
| timeoutMs | No | ||
| responseMode | No | debug |
Changes observed during successful MCP inspections.
v0.35.0Input schema / allOfPrevious value: -[
- {
- "not": {
- "required": [
- "expectedState"
- ]
- }
- }
-]New value: +[
+ {
+ "if": {
+ "properties": {
+ "platform": {
+ "const": "ios"
+ }
+ }
+ },
+ "then": {
+ "properties": {
+ "deviceId": {
+ "pattern": "^[A-Fa-f0-9]{8}(?:-[A-Fa-f0-9]{4}){3}-[A-Fa-f0-9]{12}$"
+ }
+ }
+ }
+ },
+ {
+ "not": {
+ "required": [
+ "expectedState"
+ ]
+ }
+ }
+]Input schema / properties / appId / patternPrevious value: -"^[A-Za-z][\\w]*(?:\\.[A-Za-z][\\w]*)+$"New value: +"^[A-Za-z][\\w-]*(?:\\.[A-Za-z][\\w-]*)+$"Input schema / properties / platform / enumPrevious value: -[
- "android"
-]New value: +[
+ "android",
+ "ios"
+]Input schema / properties / responseModeAdded value: +{
+ "default": "debug",
+ "enum": [
+ "compact",
+ "debug"
+ ],
+ "type": "string"
+}v0.34.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that the tool does not attach, but it does not explain permissions, side effects, return behavior, or whether probing can affect processes.
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 definition is a single front-loaded sentence with no wasted wording. It states the core action and the key non-attachment constraint efficiently.
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 tool has six parameters, conditional schema constraints, no output schema, and no annotations. The one-sentence description is insufficient to explain parameter meanings, response behavior, or prerequisites in enough detail for confident invocation.
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 0% across six parameters. The description does not clarify required parameters like platform, deviceId, and appId, nor optional ones like processId, timeoutMs, and responseMode.
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 uses a specific verb ('Probe') and names the resources ('optional platform debugger prerequisites and matching running debuggable processes'). It also explicitly rules out attaching, which distinguishes it from attach_debugger, but it does not differentiate from get_debugger_state or other debugger-state siblings.
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 phrase 'Probe optional platform debugger prerequisites' implies a preflight or discovery use case, and 'does not attach' signals a non-invasive check. However, it never explicitly says when to use this instead of attach_debugger, get_debugger_state, or other alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.