ios_observe

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds value by disclosing the compact line format, the ref-versus-coordinate convention, and the truncation behavior with concrete recovery advice. Nothing in the description contradicts the 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?

Three short paragraphs each serve a distinct purpose: define the output format, explain how to use the refs, and explain how to handle truncation. The example is compact and the most actionable information is front-loaded. There is no redundant or filler 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?

Given the output schema, full parameter coverage, and strong annotations, the description supplies the key behavioral context that is not in those structured fields: ref format and truncation recovery. It is nearly complete; explicit differentiation from ios_read_text or ios_screenshot would make it fully self-contained for tool selection.

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 for parameters is 100%, so the baseline is 3. The description adds cross-parameter guidance by explaining that query and region are the right ways to narrow a truncated result and that raising budget is not the recommended fix. This goes beyond the individual schema descriptions.

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 names a specific action and resource: 'Read the screen as a compact list of elements with short refs.' It also clarifies the output's unique role by saying refs should be passed to action tools instead of coordinates, which helps separate this from screenshot or text-reading tools. It does not explicitly name sibling tools, but the ref-based interaction model makes the tool's purpose reasonably distinct.

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 clear operational guidance: when elements are omitted, narrow with query or region rather than raising budget. This also implies the tool is meant for obtaining reusable refs before invoking action tools. It stops short of explicitly contrasting this tool with ios_read_text or ios_screenshot, so it does not fully explain when to choose this over those alternatives.

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