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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false; the description adds useful behavioral context beyond that: it is FREE, reads connected/stored data with no AI credits, and reveals that rollback_data stores the full pre-edit state before writing. This is meaningful supplement without contradicting annotations.

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 dense but each sentence earns its place: rollback mechanism, when to call, what is returned, and cost. The opening phrase 'What the pipeline can RESTORE' is slightly awkward as a noun phrase rather than an action verb, but the information is front-loaded and efficient.

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?

Given that an output schema exists, the description does not need to detail return values. It covers when to use the tool, the underlying data mechanism, what the caller can learn, how restore is triggered, and cost. For a read-only tool with one required parameter, this is complete.

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 schema already documents taskId and user_intent. The description only clarifies that the task is an 'executed task' and implies taskId is the required identifier, but it does not add significant semantic detail beyond the schema. Baseline 3 is appropriate.

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 resource (rollback state for an executed task) and what the tool returns (recoverable fields, original embed code, restore trigger). It does not explicitly name a sibling alternative or use a crisp verb like 'retrieve', but the meaning is unambiguous and distinct from task_manage and other siblings.

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?

Provides an explicit when-to-use rule: 'Call this FIRST whenever the user reports an agent edit removed, broke, or damaged something on a page.' It also gives a strong when-not-to-assume rule: 'NEVER tell the user original content is lost without checking here.' This gives the agent a clear decision procedure.

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