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

Annotations already declare readOnlyHint=false, openWorldHint=true, destructiveHint=true, so the agent knows this reaches the outside world and can have side effects. The description adds one genuinely new fact, that no task is persisted. What it omits is the consequence of running real CLICK/TYPE/SCROLL actions against a live public page under a destructiveHint=true annotation, which is exactly the risk an agent needs stated.

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 with a semicolon separating the action from the non-persistence guarantee; there is no filler and no repetition of the title. Slightly dense, but appropriately sized for the information present.

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?

The tool takes a deeply nested settings payload with zero schema descriptions, has no output schema, and sits beside similarly named siblings like get_editor_preview and cancel_editor_preview. Against that complexity, one sentence covering only page fetch, browser steps, and non-persistence leaves an agent without enough to call it correctly or choose it confidently.

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 0% and the settings object is a large nested structure with dozens of fields (actions, compareType, crop, jobSchedules, notifyConditions) that carry no descriptions at all. The description says nothing about sessionId, about what settings must contain, or which fields matter for a preview versus a saved task, so it fails to compensate for the coverage gap.

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 gives a specific verb chain and resource: fetch the configured public page, then run its browser steps for an editor preview. That is far more informative than the name alone. It stops short of a 5 because it never distinguishes itself from the sibling get_editor_preview, and 'load' vs 'get' is exactly the ambiguity an agent must resolve.

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 trailing clause 'does not save a task' implicitly signals this is a dry-run/preview step before save_task_editor, which is useful routing context. However, no explicit when-to-use, when-not-to-use, or named alternative is given, and the critical choice against get_editor_preview and cancel_editor_preview is left entirely to inference.

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