pull_adb_package

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

Goes well beyond the annotations: it discloses the local filesystem side effect (creates a package-named subdirectory), the failure precondition (must not already exist), digesting of every pulled file with SHA-256, partial-failure semantics (successful artifacts kept, per-file failure reasons), and that the device retains the originals. This is exactly the behavioral context the annotations cannot convey.

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 dense sentences, front-loaded with the verb and scope, then destination semantics, then failure/digest behavior. No filler and nothing buried.

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 description carries the return burden and does so partially: it says files are SHA-256 digested and failures are reported per file, but not how digests or failure entries are surfaced to the caller. For a mutation-style, open-world device operation with destructiveHint=false and no readOnlyHint, this is solid but not fully closed.

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 all four parameters including analysis_project_id are already documented. The description clarifies the output_directory outcome (a package-named subdirectory is created) and that the package set derives from `pm path`, but the former largely repeats the schema and the optional analysis_project_id is never mentioned. Baseline 3 is appropriate.

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 ('Pull one installed package's complete APK set (base plus every split)') and scopes it precisely: the whole package set, as enumerated by `pm path`. That specification implicitly but unambiguously separates it from the single-artifact sibling pull_adb_file.

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 context is implied by the description (pull a full installed package's APKs), but it never names an alternative such as pull_adb_file for one artifact or list_adb_packages/resolve_adb_packages to find the package name first. No when-not-to-use guidance is given; the only constraint stated (subdirectory must not already exist) is a precondition for execution, not routing advice.

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