dump_ax

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

With no annotations, the description carries full burden. It clarifies it is a DEBUG tool (suggesting read-only, non-destructive behavior) and explains the content of the dump (roles, subroles, etc.) and targeting behavior. However, it does not describe the output format (e.g., printed to console or returned as string) or any potential side effects, leaving some behavioral ambiguity.

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 sentence with a dash for additional context. It is front-loaded with 'DEBUG:' to signal intent, then states the action and purpose concisely. Every word is informative, and there is no redundant information.

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 the tool's simplicity (zero parameters, no output schema), the description is largely complete. It explains what, why, and targeting. However, it lacks explicit mention of whether the output is printed or returned, and the 'last window-captured app' prerequisite could be clearer. Still, it covers most necessary context.

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?

The input schema has zero parameters, and the description does not need to explain any. It adds value by describing the tool's function and output, which is more than the bare schema provides. For a no-parameter tool, this is adequate and exceeds the baseline.

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 purpose: dumping the accessibility tree of a target app as indented text, including specific components (roles, subroles, labels, actions, frames). It also provides the diagnostic intent (to find why elements are not marked). This distinguishes it from sibling tools that perform actions like clicking or focusing, as it is purely a debug/inspection tool.

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 indicates when to use the tool: for debugging accessibility issues, specifically to diagnose why elements are not marked. It also specifies the target (last window-captured app or frontmost). However, it does not explicitly state when not to use it or mention alternative tools, making it slightly less than a perfect score.

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