inspect_adb_device

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

Clarifies the read surface is a fixed getprop whitelist and explicitly says it is read-only with respect to the device, which usefully explains why readOnlyHint is false (the result can be retained in a project). It adds the emulator indicator detail but says nothing about failure modes for unauthorized/offline devices.

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?

One front-loaded sentence with the key scope fixed whitelist up front; every clause (versions, patch, ABIs, qemu indicator, read-only) carries information. Slightly dense but not padded.

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?

With no output schema, the enumeration of returned properties is doing necessary work and is present. The device-state prerequisites (device must be authorized/online) and what happens if the device is offline are the only real gaps.

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 100% and both parameters are documented there, so the baseline of 3 applies. The description adds context about what the whitelist reads but gives no extra syntax or constraint detail for serial or analysis_project_id.

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?

Specific verb (inspect) plus a precisely scoped resource (one device's build identity via a fixed getprop whitelist), and it enumerates the properties returned. This clearly separates it from list_adb_devices (enumeration) and inspect_adb_package (package-level 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 'one device' framing implies you need a serial already, but it never states when to reach for this instead of list_adb_devices, list_adb_features, or collect_adb_bugreport. Usage is inferable from the sibling set rather than stated.

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