ui_list_dialogs

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

Annotations already declare readOnly/destructive=false, but the description adds a behavior those hints do not convey: it guarantees the call will not dismiss, confirm or accept the dialog, which matters for an open-world UI tool where reading could plausibly mutate state. It does not address idempotency or what data about each dialog is surfaced.

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?

One sentence, front-loaded with the verb and resource, and every clause earns its place by adding the non-interaction guarantee. No filler or restatement of the name.

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 no-required-param, read-only inspection tool with full schema coverage and annotations, the key constraint (it will not alter dialog state) is present. Slight gap: it doesn't say whether it returns dialog text/buttons or what happens when no dialogs are visible.

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 100%, so both parameters are fully documented upstream, and with zero required parameters the baseline is 3. The description adds nothing about target_id or expected_layout_id, and notably the schema notes target_id is 'Required for changes', which is odd for a read-only tool and unexplained here.

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 (inspect) and resource (visible dialogs), and the clause 'without dismissing, confirming or accepting them' further distinguishes it from interaction tools like alert_prepare or emergency_stop. It is clearly separable from siblings like ui_snapshot and ui_list_panels by its dialog-specific scope.

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 negation clause implicitly tells the agent when to use this instead of an action tool, but there is no explicit routing guidance, no statement of preconditions (e.g. target_id from browser_list_tabs), and no named alternative to use when a dialog must actually be dismissed.

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