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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds genuinely non-obvious behavior: that the run continues if the client disconnects, and that MCP Apps clients render completed image/video/audio output in an interactive preview. It stops short of describing terminal status values or polling guidance, so not a 5.

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 sentences, front-loaded with the returned fields, and the second sentence adds a useful behavioral caveat. The first sentence is a long comma-list that is dense but each item is informative; minimal waste overall.

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?

With no output schema, the description correctly takes on the job of enumerating return fields, including error and pending-approval cases, which is the critical gap for a status tool. It omits what the possible status values are, which would help an agent decide when to stop polling.

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?

Only one parameter and schema coverage is 100%, so the schema already explains that runId is an opaque ID returned by brand creation, chat send or node generation. The description adds no format, length, or lookup behavior beyond that, so the baseline 3 applies.

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 ("Returns") and enumerates the exact resource contents: status, current step, pending question/approval, error, output node/asset IDs, and chat reply text. It also scopes which run types it covers (brand, chat, generation), which is enough to separate it from siblings like fuzz_read_chat or fuzz_get_node.

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?

Usage is only implied: the phrase "asynchronous ... run" plus runId hints this is a polling tool for runs created elsewhere. It never explicitly says when to use this instead of fuzz_read_chat or fuzz_get_node, nor does it say whether to poll or how often. Adequate but leaves routing to inference.

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