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

Beyond the annotations (destructive/not idempotent), the description adds substantial behavioral context: edits spend credits, returns include a skipped_mutations list with applied/reason that the agent is told to check, project_note affects up to 10 scenes per call, scene lengths follow narration, and image/clip/voiceover layers cannot be removed. This is exactly the surplus detail the annotations cannot convey.

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 one-line purpose is front-loaded before the dense action breakdown, and every clause carries information (credits, return shape, layer constraints). It is a single semicolon-heavy block rather than cleanly separated sections, which slightly hurts scanability but there is little filler.

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 13-parameter, destructive, credit-spending tool with no output schema, the description covers the key gaps: credit cost, the skipped_mutations return and its semantics, per-action limits, and layer constraints. It omits auth/permission requirements and the return shape beyond skipped_mutations, so it is strong but not exhaustive.

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, but the description adds meaning not fully in the schema: captions act as a merge, music is timed in seconds and a track's duration follows from its trim, and the action-level parameter groupings mirror the enum. That extra semantic framing lifts it above baseline.

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 resource (the video in the editor) and enumerates the six distinct actions it can perform (scene_note, project_note, captions, add_sfx, add_music, update_music), so an agent can tell the scope apart from a read tool. The opening 'Polish the video' is generic, and it never explicitly names sibling tools like editor_read as the reading counterpart, so it stops short of a 5.

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?

Each action is tied to a clear condition: scene_note for one scene, project_note for the whole video (10 scenes per call), captions to merge settings, add_sfx to attach a sound effect, add/update_music for background music. However it gives no explicit 'when not to use this' exclusion or direct routing to editor_read/segment_edit alternatives.

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