inspect_adb_window

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

The description declares the tool 'Read-only,' while the annotations set readOnlyHint=false. An agent reading both signals receives conflicting guidance about whether calling this mutates device state. The dumpsys framing is informative ('without any interaction'), but the direct conflict with the structured annotation is disqualifying under the rubric.

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 tightly packed sentence, front-loaded with the verb and resource, followed by the mechanism and the read-only claim. No filler text.

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 two-parameter snapshot tool with no output schema, the description says enough: what is read, from which dumpsys target, and that no interaction occurs. It stops short of describing the returned shape, but the enumerated field names largely cover that.

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%, so both the required 'serial' and the optional 'analysis_project_id' are fully documented in the schema with patterns and semantics. The description adds no parameter-level detail, which is acceptable given the schema already carries that load, but nothing is gained either.

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 ('Report') plus a precisely scoped resource: the window manager's focus declarations, naming the exact dumpsys fields (mCurrentFocus, mFocusedApp). It is clearly separable from siblings like capture_adb_screen or inspect_adb_display, which produce pixels rather than focus state.

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 clause 'what is on screen at read time without any interaction' implies this is the non-invasive alternative to capture_adb_screen, but no sibling is named and there are no explicit when-not conditions. Usage must be inferred rather than read.

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