ios_screenshot

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description goes beyond that with two non-obvious behaviors: annotate_refs forces a fresh screen re-read (costing a tree fetch) and requires the 'vision' extra to be installed. It stops short of describing the return payload or device/session prerequisites, so it is strong rather than complete.

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?

Front-loaded with the core purpose, then usage, then caveats — a sensible ordering. Every sentence carries information, though the third paragraph could be folded more tightly into the second without loss.

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 single-boolean, zero-required-parameter tool with annotations and no output schema, the definition covers purpose, selection criteria, dependency, and cost. The only gap is how the image is returned (path vs. inline data), which the missing output schema leaves unaddressed.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: the boxes are labelled with refs you can act on, and the refs are guaranteed current because annotating re-reads the screen. That 'fresh refs' semantics plus the cost implication is more than the schema's 'using fresh refs' alone conveys.

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?

Opens with a specific verb+resource: 'Capture the screen as an image.' It is immediately distinguishable from ios_observe, ios_read_text, and ios_find, and the annotate_refs sentence clarifies the secondary capability (boxed refs for visual selection).

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?

Gives explicit triggering conditions: no accessibility label, layout matters, or ios_observe cannot find something visible. It also names the downstream action ('pass it to an action tool'), so the agent knows how this fits into a workflow rather than just when to call it.

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