dream_cancel

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

With no annotations, the description carries the full burden, and it does add one genuinely valuable behavioral fact: running clips are not interrupted, so the effect is limited to the pending queue. However, it omits whether the removal is reversible, what happens to the queue record, whether any auth/permission is needed, and what the call returns.

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 short sentences, effect first and the non-interruption guarantee second. Nothing is wasted and the operative constraint is front-loaded.

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 parameterless, no-output-schema tool, the description is nearly sufficient: the scope and the key safety boundary are stated. It could still say what happens to already-queued metadata or what the caller gets back, but that is a minor gap for a zero-arg operation.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The empty schema is consistent with a bulk 'clear pending' action.

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?

The description states a specific action and its scope: remove all not-yet-started generation jobs, while leaving running clips alone. That distinguishes its effect from dream_generate/dream_edit, but it never names any sibling or explicitly frames itself as the 'cancel/clear queue' counterpart, so an agent must infer positioning from the list.

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?

It gives an implicit condition (items that have not started) but no guidance on when to prefer this over alternatives such as letting jobs finish or checking dream_status first. There is no when-not-to-use and no mention of the sibling tools.

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