Take Eden Screenshot

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

With only title in annotations, the description carries the full behavioral burden. It discloses the optional save side effect and explicitly warns 'Do not cache screenshots.' However, it does not mention overwrite behavior when saving, whether the operation is read-only, or any error handling. It adds some value but lacks depth.

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 exceptionally concise, with four short sentences. It front-loads the primary action and each sentence adds distinct information: what is captured, optional saving, usage guidance, and a caching constraint. No wasted words.

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?

Given the low complexity of a screenshot tool and the absence of an output schema, the description covers the essential context: return value (PNG image), pixel dimensions for touch coordinates, and the optional save_path. Missing session_id explanation and edge cases like overwrite prevention, but overall sufficient for an AI agent.

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 has 2 parameters with 0% description coverage. The description explains save_to as 'Optionally save a copy to an absolute or relative .png path', adding useful format details. However, session_id is not mentioned at all, leaving its purpose implied from sibling tools. Partially compensates for the schema gap.

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 uses the specific verb 'Capture' with the resource 'current Eden render surface' and clearly states the output is a PNG image. It also distinguishes from siblings like eden_get_screen_size (which returns dimensions, not an image) and eden_capture_sequence (which likely captures multiple images) by focusing on a single current render surface.

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 gives clear context on when to use the tool: when you need a screenshot and specifically to use the returned image's pixel dimensions for subsequent touch coordinates. It also advises against caching. However, it does not explicitly mention alternatives or when *not* to use it, such as when only dimensions are needed (which would be eden_get_screen_size).

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