Verify Action

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

With no annotations provided, the description carries the transparency burden. It usefully discloses behavioral semantics such as 'gone (not visible)', 'app (foreground package or name)', and 'changed (the last action changed the screen)'. However, it does not explain matching behavior, side effects, permission needs, or failure behavior.

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 compact and front-loads the core purpose before giving the kind list. It contains no filler, though the single run-on sentence is dense and could be structured more clearly.

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?

Despite having an output schema, the tool context is underspecified: no annotations, no guidance for key parameters, no alternative routing, and only minimal behavioral detail. An agent cannot fully determine correct usage, especially around OCR, device targeting, and timeout behavior.

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 0%, so the description must compensate for all five parameters. It only adds real meaning to 'kind' and partially to 'expected' by implication. 'device', 'timeout', and 'use_ocr' receive no explanatory treatment, leaving the agent to guess their semantics.

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's function: verify an outcome against the live screen. It enumerates supported verification kinds (text, gone, app, activity, changed), making its purpose concrete. However, it does not distinguish itself from the similarly named sibling 'validate_action'.

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 provides no guidance on when to use this tool versus sibling alternatives like validate_action, wait_for, or read_screen. It implies usage through the kind list, but does not state exclusions, prerequisites, or recommended scenarios beyond the terse kind definitions.

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