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

Annotations already cover the safety profile (destructiveHint=true, readOnlyHint=false), so the description's job is to add context. It does: it discloses that resources are freed and, usefully, that the next start_preview incurs a cold boot, a restart-cost trait not present in the annotations. It does not explicitly state that live preview state is discarded.

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?

Two tight sentences, purpose front-loaded ahead of the consequence note, with zero filler. 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?

For a one-parameter teardown tool with no output schema and annotations already covering safety, the description is nearly sufficient: purpose plus restart consequence are covered. Minor gaps remain around unsaved-state loss and behavior when no preview is running.

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 single parameter flowId is never named or explained in the description. The phrase "the flow's preview" implies a flow identifier is needed, which partially compensates, but with one undocumented parameter the description leaves the argument semantics to inference.

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?

Specific verb (stop) plus a precise resource (the flow's preview sandbox), and it names the counterpart operation start_preview, which lets an agent separate it from flow_get_preview_status and flow_sync_preview. It stops short of explicitly contrasting with those other preview siblings, keeping it at 4 rather than 5.

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?

No explicit when-to-use or when-not-to-use guidance; the agent must infer that this is called to tear down a preview. The cold-boot note hints at a trade-off but never states conditions, prerequisites, or alternatives such as whether a running preview is required.

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