read_adb_setting

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

The description adds a genuinely useful behavioral trait ('Absent keys report the device's own null observation'), which annotations do not convey. However, it declares 'Read-only' while annotations set readOnlyHint=false, a direct conflict on the same axis; the annotation set (destructiveHint=false, idempotentHint=true) supports the read characterization, so the contradiction is likely a conservative annotation rather than a true write, but the two signals still disagree.

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 short, front-loaded sentences: what it reads, how absent keys behave, and what it is not. No boilerplate, no repetition, nothing wasted.

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?

There is no output schema, yet the description never indicates what the result looks like (a raw settings string versus a structured object) or how it appears when the key is absent — 'null observation' is evocative but underspecified. Device prerequisites and the purpose of `analysis_project_id` are also left to the schema.

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%, so every parameter is already documented, including the serial format and namespace enum; the description merely restates the namespace options already enumerated in the schema. It never mentions the optional `analysis_project_id` retaining behavior in prose, adding little beyond structured data.

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 ('Read one settings value') and scopes it to the three namespaces, with the underlying `settings get` command named for precision. It is clearly distinguishable from the many list_adb_*/inspect_adb_* siblings, though it never explicitly contrasts itself with them.

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?

Usage is implied: read a single setting from system/secure/global. 'Writing settings is not exposed' usefully rules out a write counterpart the agent might look for, but there is no explicit when-to-use, no prerequisites about device connectivity or needing a serial from list_adb_devices, and no alternatives offered.

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