get_screen_state

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

No annotations are provided, so the description carries the full burden. It discloses the return payload and implies a read-only observation, but says nothing about permissions, rate limits, or whether the tree can be stale or large. It is enough to call the tool safely but thin on behavioral context.

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 sentences with zero filler. The primary purpose leads and the workflow directive follows, which is the right front-loading for an orientation tool.

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?

With no output schema and no annotations, the description does the necessary work of naming returned fields and describing how the result is consumed downstream. It is nearly complete for a zero-required-param read tool, though it omits the filter toggle that affects the payload.

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 description coverage is 100% and the single filter parameter is fully documented in the schema, so the baseline is 3. The description never mentions the filter option or what 'simplified tree' means, adding no meaning beyond the schema.

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?

States a specific verb and resource ('Returns the current UI accessibility tree') and enumerates the returned content (text, class names, bounds, phone state, screen dimensions). It does not explicitly differentiate itself from overlapping siblings like get_element_tree, get_phone_state, or get_screenshot, so it falls short of a 5.

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 a clear ordering directive ('Call this first to understand what is on screen') and names the downstream tools that consume its output (tap / swipe / keyboard_input via returned bounds). Strong context, but no exclusion criteria for when to prefer get_screenshot, get_element_tree, or get_phone_state instead.

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