list_packages

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

No annotations are provided, so the description carries the full behavioral burden. It discloses only the data source and that keyword filtering is possible; it says nothing about return format, whether system/third-party apps are both included, permissions or ADB/adb-server requirements, or result size/ordering.

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 short sentence with zero filler; the core purpose and the filtering capability are front-loaded and nothing is redundant.

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 annotations and no output schema, the description must stand on its own. It is adequate for a trivial two-parameter lister whose schema is fully documented, but it leaves return shape, app scope and device prerequisites unspecified.

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% for both parameters, so the schema already documents serial and keyword. The description merely restates the keyword filter (and omits serial entirely), adding no semantics beyond the structured fields — baseline 3 applies.

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 (列出) and resource (设备上已安装的应用包名), so an agent can immediately tell this enumerates installed packages rather than devices or APK files, unlike siblings such as list_devices or pull_apk. It does not explicitly name or contrast any sibling, which keeps it short of a 5.

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 only implied: the verb and scope make it obvious this is the enumeration step (e.g. before pull_apk or detect_packer), but there is no explicit when-to-use, no prerequisites (ADB connectivity, serial required for multi-device), and no named alternatives or exclusions.

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