dump_ax

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

With no annotations, the description carries the full burden. It usefully discloses the output shape (indented text) and target resolution ('current AX/UIA app, or frontmost'), but never states that it is a non-mutating/read-only operation or any performance/cost characteristics, leaving the safety profile to inference.

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?

A single, front-loaded sentence prefixed with DEBUG, using the em dash to separate the action from the diagnostic rationale. Every clause earns its place with no filler.

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 zero-parameter debug tool with no output schema, the description supplies everything an agent needs: what is dumped, what fields it contains, the output format, and which app it resolves to.

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 tool takes zero parameters, so per the baseline there is nothing for the description to disambiguate. The mention that it targets the current AX/UIA app or frontmost is a small bonus, but the baseline of 4 applies for a 0-param 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 ('dump') and resource ('target app's Accessibility tree') and enumerates what the dump contains (roles, subroles, labels, actions, frames). The DEBUG framing and diagnosis intent clearly separate it from siblings like ax_read, read_ui, and inspect_app.

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 clear context for use: diagnose why some elements are not exposed, distinguishing it from normal read/inspect tools. It does not state when NOT to use it (e.g., prefer ax_read for straightforward reading), so no explicit exclusions or named alternatives.

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