Polls until the job completes, returning file paths; if not done by timeout, returns the intermediate image. Call again to continue.
Wait for a job to finish and return the file paths. Polls the bridge until the timeout; returns the intermediate picture if it is not done yet — that is not an error, just call again.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | ||
| timeoutSec | No | How long to wait, default 600 (a Seedance 2.5 clip takes 1–5 min) |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose non-obvious behavior: it polls the bridge up to a timeout, and a partial/intermediate result is explicitly not an error — an agent might otherwise treat it as a failure. It omits auth/permission needs and rate-limit or bridge-failure behavior.
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, front-loaded with the primary outcome (file paths) and then the polling/partial-result caveat. The em-dash clarification earns its space by preventing a misread of the intermediate return.
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?
No output schema exists, so the description correctly describes return values (file paths on completion, intermediate picture otherwise). This is sufficient for an agent to call and interpret it, though it could say more about what happens on timeout exhaustion or bridge errors.
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 coverage is 50%: timeoutSec is documented in the schema with a default, but jobId has no description. The description reinforces the timeout's meaning by saying it polls until the timeout, but adds no format or origin detail for jobId, so it only marginally compensates.
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+resource: wait/poll for a job to finish and return file paths. It implicitly distinguishes itself from the non-blocking dream_status by describing polling until a timeout, but never names the sibling, so the differentiation is inferred rather than stated.
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?
Conveys the usage context (block until a job completes, re-call if not done) but gives no explicit guidance on when to prefer dream_status or dream_cancel over this blocking wait, nor any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.