resolve_adb_packages

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

The description closes with 'Read-only,' but the annotations declare readOnlyHint=false, a direct conflict on the tool's side-effect profile. Because the two structured and unstructured signals disagree about whether this operation is a pure read, an agent cannot trust either, so no credit is available for the otherwise useful disclosure of the return value (base APK device path).

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 sentences with the matching rule and return value front-loaded, followed by the workflow hint and the safety claim. No filler, no restatement of the title.

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 3-parameter lookup with a fully-described schema and no output schema, the description covers purpose, matching behavior, return value, and the follow-up call. It omits edge behavior (no-match result, ambiguity when multiple packages match, minimum query length) and the role of `analysis_project_id`, but nothing essential is missing.

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 the schema already documents case-insensitive substring matching and the device serial format, so the schema does the heavy lifting. The description's `whatsapp` → `com.whatsapp` example adds only marginal illustrative value over the schema's own example, and it says nothing about the optional `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?

States a specific verb and resource ('Find installed packages') plus the exact matching semantics (case-insensitive substring) and a concrete example (`whatsapp` → `com.whatsapp`). It also states what is returned ('each match's base APK device path'), which lets an agent distinguish it from `list_adb_packages` and `inspect_adb_package` without opening a schema.

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?

Explicitly positions the tool as 'the first step of an easy get: resolve, then pull_adb_package the exact name', giving a concrete chaining instruction and naming the follow-up sibling. It stops short of stating when NOT to use it (e.g. when you want a full listing from `list_adb_packages` or already know the exact package name).

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