explore_screen

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It doesn't explain whether this reads the accessibility tree, widget tree, or does semantic analysis, what output form it produces, whether it explores recursively or top-level only, or what the 'within' constraint does to behavior. For a screen-exploration tool, these behavioral details matter significantly.

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?

The description is a single concise sentence with zero waste. However, it's under-specified given the tool's complexity—a one-liner is economical but doesn't earn beyond a 4 because the conciseness comes at the cost of completeness.

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 tool with two optional parameters, no annotations, no output schema, and a vague purpose, the description should provide significantly more context. An agent cannot determine what 'explore' returns, how it differs from widget/accessibility tree queries, or what filtering semantics apply. The sibling ecosystem (get_widget_tree, get_accessibility_tree, screenshot) makes this tool's unique value unclear.

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%, so both parameters (filter, within) are already documented in the schema. The description 'Maps out interactive elements' adds a general sense of what the output is but doesn't clarify how 'filter' and 'within' interact or what values are valid (e.g., what flags beyond isButton/isTextField are supported). Baseline 3 is appropriate since schema covers everything.

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 'Maps out interactive elements on the screen' has a clear verb+resource ('Maps out...elements on the screen'). However, it doesn't distinguish itself from siblings like 'get_widget_tree' or 'get_accessibility_tree', which could serve similar roles, and 'explore_screen' sounds like it could overlap with screenshot or widget inspection functions.

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?

No guidance on when to use this tool versus sibling tools like get_widget_tree, get_accessibility_tree, or screenshot. There's no context about when exploration is preferred over querying widget/accessibility trees directly, nor any exclusions or alternatives mentioned.

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