Inspect Android capabilities

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

Annotations already indicate read-only (readOnlyHint=true), idempotent (idempotentHint=true), and non-destructive (destructiveHint=false). The description adds the specific capability types probed (ADB, input, etc.), which provides some behavioral context beyond annotations. However, it does not disclose potential side effects like network usage or time cost.

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 focused sentence of 14 words, front-loading the key information. No extraneous content.

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 tool with an output schema and clear annotations, the description lacks context about when this inspection is necessary (e.g., before certain mobile actions). It is adequate but not complete in guiding the agent's workflow.

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 covers 50% of parameters (serial described, refresh only type/default). The description does not elaborate on the 'refresh' parameter or add any meaning beyond the schema. For a 2-parameter tool with partial schema coverage, the description should compensate but fails to do so.

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 it probes the device's ADB, input, command, build, and backend capabilities. It uses a specific verb ('probe') and a clear resource ('capabilities'), and distinguishes from siblings like mobile_devices_list (listing devices) and mobile_app_inspect (app-specific inspection).

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 provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as having a device serial from mobile_devices_list, or when not to use it. Sibling tools exist for similar purposes but no distinction is made.

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