mobile_act

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

Annotations provide no safety hints (all false), and the description adds that value text is never echoed or stored, and returns compact state. However, it does not disclose potential destructive actions (e.g., reset) or side effects beyond the return.

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 concise sentences front-load the purpose and key usage, with no wasted words. Every line adds value.

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 7 parameters, no output schema, and minimal annotations, the description covers core behavior but omits error handling, action details, and return format beyond 'compact state'. Additional completeness would help for such a complex tool.

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?

With only 43% schema coverage, the description adds meaning to target (@m refs) and observe (compact state), but fails to document snapshot or timeoutMs parameters. The schema enums for action and observe are clear, but no additional context is provided.

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 operates MobileNAV with actions like tap/type/wait, and distinguishes from mobile_observe by returning compact state. However, it doesn't explicitly list all actions or define 'MobileNAV', leaving some ambiguity.

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?

The description advises using @m refs for target parameters and implies using this tool instead of mobile_observe for state, but lacks explicit when-to-use or when-not-to-use guidance compared to siblings like browser_act.

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