Observe Page Dialog

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces non-destructive behavior by stating 'without handling it'. It also adds context about the specific dialog types (alert, confirm, prompt) and the 'bounded message' return, which clarifies the tool's behavior beyond the annotations. It does not describe behavior when no dialog is pending, but the timeout parameter partially covers this.

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, focused sentence, front-loaded with the action and purpose. Every word contributes value; there is no redundancy or filler, fitting the tool's simplicity.

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 simple observation tool, the description, combined with the comprehensive schema and annotations, is largely complete. It clearly conveys the tool's function and non-destructive nature. The behavior when no dialog appears is implied via the timeout and schema, though not explicitly stated in the description, which is a minor gap.

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 the parameters are already well-documented. The description adds minimal value beyond the schema, only tying 'bounded message' to the max_message_chars concept. No parameter details are missing, but the description also does not enrich understanding beyond what the schema provides.

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 identifies the tool's action ('Observe a pending native alert, confirm, or prompt') and its scope ('return its bounded message without handling it'). This distinguishes it from sibling tools like page_dialog_respond, which handles the dialog, and page_observe, which observes page state.

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 clear context for when to use the tool: when a native dialog is pending and only observation is desired, explicitly stating it does not handle the dialog. It does not name alternative tools or provide when-not conditions, but the 'without handling it' implies a contrast with page_dialog_respond, giving adequate guidance without explicit exclusions.

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