assemble

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

With no annotations, the description discloses that the tool is a blueprint and the NLE cut is manual. It mentions optional clip attachment but does not describe side effects like overwriting or append behavior, permissions, or rate limits. The absence of destructive/read-only hints means the agent must infer 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?

The description is concise with no wasted sentences. It front-loads the core purpose and includes a standard Args block. Minor improvement could be separating the background info from parameter details.

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 2-parameter tool with no output schema, the description covers purpose and parameters adequately. However, it does not describe the return value (the manifest structure), error conditions, or explicitly state that a plan must exist beforehand.

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 schema has 0% coverage (no parameter descriptions), but the description adds meaning: 'project: project name' and 'clips: optional rendered-clip refs keyed by shot_id.' This clarifies the purpose of the clips parameter far beyond the schema's anyOf definition.

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 clearly states the tool builds a cut manifest with shot order, durations, and audio notes. This specific verb+resource combination distinguishes it from sibling tools like plan_shots or lock_campaign.

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 explains that the tool uses a plan for order/timing and that clips are optional. It also clarifies that the actual NLE cut remains manual in v1, providing context on when this is an intermediate step. However, no explicit when-not-to-use or alternative tools are mentioned.

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