native-describe-screen

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

With no annotations, the description carries full burden. It thoroughly discloses return contents (flat list of leaf elements, frames, tapPoints, normalized fields, traits, labels) and behavioral quirks (statuses for not-connected apps, restart logic, service_stale requiring tool-server restart, connect_pending meaning do not restart, init_failed requiring simulator reboot, rejection of Apple system apps). This is exceptionally transparent.

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?

Despite being long, every sentence adds valuable information. It front-loads the core purpose, then details output, usage context, and error handling in a logical order. No fluff or repetition; the length is justified by the tool's complexity.

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?

The tool is complex (low-level native inspection with multiple statuses and failure modes) and lacks an output schema. The description fully compensates by explaining return values, usage scenarios, and detailed error recovery steps. It also clarifies the relationship with the describe tool, ensuring complete context for an 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?

Schema coverage is 100%, so all four parameters have descriptions in the schema (udid, bundleId, skipClasses, skipClassPrefixes) with helpful examples. The description does not add extra parameter semantics beyond what the schema already provides, so a baseline of 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 clearly states the tool reads the running app's native accessibility screen description via injected devtools, and distinguishes it from the sibling 'describe' tool by calling it a low-level native inspection tool with raw point-space geometry. It explicitly mentions the separate public describe contract.

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?

Explicitly says 'Use when you are evaluating or debugging the lower-level native data behind the public describe tool, or when you need its raw point-space geometry rather than describe's normalized contract.' It also provides detailed status handling instructions (restart_required, service_stale, connect_pending, init_failed) and failure modes (Apple system app rejection), making when-to-use and how-to-handle conditions very clear.

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