xae_dialogs

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

Beyond the readOnlyHint annotation, the description discloses real behavioral detail: a pending dialog blocks all COM calls, buttons are read via UI Automation, unreadable buttons yield null plus a buttons_note, and an 'unidentified' state exists when the shell is modal but no window can be named. These edge-case disclosures materially help an agent interpret results.

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?

Content is dense and front-loaded with the core fact (open dialogs block COM calls) before the edge-case caveats. Some parenthetical asides (WPF About / Options, WinForms) add flavor that could be trimmed, but overall every sentence carries 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?

With an output schema present, the description needn't restate return values, and it covers the critical operational fact (blocking) and known ambiguity states. The only notable omission is routing to xae_dialog_resolve for remediation, which keeps it from a 5.

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 there is nothing to document; baseline 4 applies. The description correctly focuses on output shape instead of inventing parameters.

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 states a specific resource set: modal dialogs open in the XAE shell plus the watchdog's auto-answer rules and log, enumerating the fields returned (title, class, text, buttons). It is clearly an inspection/list tool and distinct from mutation siblings, though it never names xae_dialog_resolve, the obvious counterpart, so separation is only implicit.

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 line 'a pending dialog blocks every COM call' gives a strong implied reason to call this before other XAE operations, but the description never explicitly says when to call it or that xae_dialog_resolve is the tool for acting on a found dialog. Usage is inferable rather than stated.

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