ios_screenshot

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

Annotations already mark the action as read-only, idempotent, non-destructive, so no safety disclosure is needed. The description adds useful behavioral context beyond that: screenshots are needed for visual/layout scenarios, and annotate_refs labels boxes with refs from the last observation, which tells the agent how to exploit the output for follow-up actions.

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 sentences, no filler. The core purpose is first, the usage guidance is second, and the only parameter's behavioral effect is explained third. Every sentence earns its place and the length is proportionate to the tool's simplicity.

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 screenshot tool with one optional boolean and strong read-only/idempotent annotations, the description fully covers what the tool does, when to reach for it instead of ios_observe, and what annotate_refs does. No critical missing information remains for correct selection and invocation.

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 sole parameter annotate_refs is already fully described in the schema (draw numbered boxes over elements from the last observation). The description repeats this in different words and adds the rationale 'so you can pick one by eye', but does not materially expand the schema's definition. With 100% schema description coverage, 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 states a specific verb and resource ('Capture the screen as an image') and immediately distinguishes this tool from ios_observe by explaining when it is needed: missing accessibility labels, layout concerns, or things visible but not observable. This makes the tool's identity and boundary clear.

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 gives explicit conditions for use: when an element has no accessibility label, when layout matters, or when ios_observe cannot find something visible. It also names the alternative ios_observe, giving the agent enough to choose correctly without needing further context.

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