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

Annotations already establish the safe read profile (readOnlyHint, idempotentHint, non-destructive), so the bar is lower, and the description adds real value: it discloses that runs survive client disconnection, that pending questions/approvals can be surfaced, that errors are returned, and that MCP Apps clients render interactive previews. It stops short of describing rate limits, cursor semantics, or whether polling frequency matters.

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?

Three tight sentences with zero filler, front-loaded with the return payload before the lifecycle and client-rendering details. Every sentence conveys distinct 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?

With no output schema, the description correctly carries the burden of describing return content (status, events, questions/approvals, errors, asset IDs) and does so thoroughly. The one gap is the pagination/cursor flow, which is left entirely to the schema.

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% and both parameters (runId, cursor) are fully documented in the schema as opaque values. The description adds no additional semantics about either parameter, 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 resource ('status, progress events, pending questions or approvals, errors and output asset IDs of an asynchronous brand, chat or generation run'), enumerating the payload so the agent knows exactly what it retrieves. It is clearly distinguishable from read-oriented siblings like fuzz_get_asset or fuzz_read_chat because it is scoped to asynchronous run tracking.

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 implies the polling use case by framing the run as asynchronous and noting it continues if the client disconnects, which hints that this tool is how you resume/monitor work. However, it never explicitly states when to prefer it over siblings such as fuzz_read_chat or fuzz_get_node, nor does it mention the cursor-based pagination workflow. Usage is implied rather than directed.

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