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

Adds substantial context beyond annotations: the original video is untouched, unchanged scenes keep their existing images, and the revise step charges nothing while the subsequent render does (narration re-voiced, video re-assembled). This cost/side-effect disclosure is exactly what annotations (readOnly=false, destructive=false) 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?

Front-loaded with the action and the key behavioral fact (new draft, original untouched), then the cost model, then the follow-up tool. No wasted sentences despite packing in several distinct facts.

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 4-param mutation tool with no output schema, the description covers the full lifecycle: what is created, what is preserved, what it costs, what to do next, and what is not supported. Nothing essential is missing.

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 75% — scene, visual, and narration are documented in the schema, but videoId has no description in either place. The description adds no parameter-level detail, so the schema is doing the work; baseline 3 is appropriate with a minor gap on videoId.

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 and resource ('change one scene of a video that was already rendered') and immediately clarifies the mechanism (creates a NEW draft copying all scenes). This clearly separates it from autoshort_update_draft and autoshort_render_draft siblings.

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?

Explicitly names the follow-up step (show to user, then autoshort_render_draft renders it) and names the unavailable alternative ('single-scene re-render inside the existing file is not available yet'), so an agent knows both what to do next and what not to attempt.

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