pull_database

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

Since no annotations are provided, the description is the sole source of behavioral transparency. It does disclose the method (adb run-as) and destination (local cache), which is helpful, but it doesn't mention whether the operation is read-only on the device, what happens if files already exist, expected permissions, or failure scenarios. These gaps make it only partially transparent.

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?

The description is a single, compact sentence that front-loads the core action and includes key details (SQLite, WAL, source, destination, mechanism). Every word contributes to understanding; no filler or redundancy.

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?

Although the tool is simple (2 required parameters, no output schema), the description omits important context such as return value (e.g., stored path), usage prerequisites, and edge-case behavior. The lack of annotations increases the burden on the description, and it does not fully cover what an agent needs to know to invoke correctly and interpret results.

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?

The input schema already describes both parameters (appId and dbName) with 100% coverage. The description does not add any additional meaning to the parameters, such as format constraints or examples beyond what the schema provides. 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?

The description clearly states the action ('Extracts'), the resource ('SQLite database and its WAL files'), the source ('Android device'), and destination ('local cache'), making it instantly distinguishable from sibling tools that list or query rather than pull data. The specific mention of adb run-as further clarifies the scope.

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 description implies when to use it (when you need to extract an app's database files) but doesn't explicitly state alternatives or exclusions. For example, it doesn't mention that execute_query is for live queries or that list_databases is for discovery. No explicit 'use this instead of' guidance is provided.

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