phone_screenshot

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

With no annotations, the description carries the full burden. It earns credit for disclosing dependencies and the non-obvious capture-by-window-id behavior that works even when the window is occluded. It does not say what is returned (image payload vs. file path) or what happens on failure, which an agent needs for a no-annotation tool.

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?

Two compact sentences with zero filler, and the most decision-relevant token (EXPERIMENTAL) is front-loaded ahead of the prerequisites and the behavior.

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 zero-parameter tool, prerequisites and the occlusion-proof capture quirk are the key unknowns, and both are covered. The remaining gap is the return format, which no output schema compensates for.

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?

Zero parameters, so the baseline is 4 per calibration; there is nothing for the description to disambiguate and the empty schema is self-evident.

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?

Specific verb+resource: 'Screenshot the iPhone screen', with the target qualified as the Mirroring window. Among siblings mac_screenshot and browser_screenshot, the device qualifier makes the distinction immediate without opening any schema.

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?

It states hard prerequisites (iPhone Mirroring running, python3 with pyobjc) and flags EXPERIMENTAL status, which implies 'use only if you have this setup'. But it never says when to pick it over phone_ocr or mac_screenshot, nor what to do when the prerequisites are unmet.

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