take_app_screenshot

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

Annotations indicate read-only, idempotent operation. Description adds valuable context: case-insensitive matching, 5-window limit, requirement for on-screen windows, and error conditions. No contradiction with annotations.

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?

Concise and well-structured: first sentence states core purpose, followed by limitations and note, then structured Args/Returns/Raises. No extraneous content.

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 simple tool with one parameter and no enums, the description covers purpose, limitations, return format, and common errors. The existence of an output schema is noted; the description sufficiently explains output.

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 only parameter, app_name, is described as 'Full or partial app name to match' with case-insensitive behavior. This adds meaning beyond the schema's type string, but could be more explicit about whether it's a substring or fuzzy match.

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?

Clearly states the tool takes screenshots of all windows for an app using a case-insensitive substring match. Distinguishes from sibling tools like take_window_screenshot and take_simulator_screenshot by specifying scope (app vs window vs simulator).

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?

Provides context on when the tool works (only apps with on-screen windows) and behavior (up to 5 windows, multiple apps error). Does not explicitly compare to alternative screenshot tools, but the mention of 'case-insensitive substring match' and limitation of 5 windows offers sufficient guidance.

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