dream_generate

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

With no annotations, the description carries the full burden. It does disclose the key behavioral trait — asynchronous queueing with an immediate jobId return rather than the clips — and that file paths are absolute and read by the bridge. It omits permissions/auth needs, credit-charging side effects, and failure behavior when validation fails.

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 compact clauses, zero padding, and the critical async behavior and the sibling routing are front-loaded before the path detail. Every sentence earns its place.

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 an 8-parameter async generation tool with no output schema, the description covers the essential unknown — that it returns a jobId immediately and that waiting is a separate call — and clarifies path semantics. It is nearly complete, missing only what happens on validation/credit failure and any permission requirements.

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 baseline is 3. The description only marginally adds: it clarifies that refs/frames paths are absolute and read by the bridge, which the schema does not state. The other seven top-level parameters are left entirely to the schema.

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 ('Queue a Seedance 2.5 generation') plus the execution context ('in the live Dreamina through the extension'), and explicitly separates itself from dream_wait. An agent can distinguish it from dream_wait without opening a schema.

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?

Routes explicitly to the alternative for the blocking case: 'Returns jobId immediately WITHOUT waiting for the clips — wait with dream_wait.' Clear context, but it gives no guidance on when to pick this over siblings like dream_edit, and no stated preconditions beyond that.

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