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

Annotations already declare non-read-only, non-destructive, non-idempotent, so the safety bar is lower. The description adds the non-obvious lifecycle precondition (must precede approve_script), though it doesn't say what happens if that precondition is violated or whether the call is rejected.

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, zero filler, and the most constraining fact (the pre-approval window) is front-loaded before the parameter note.

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 3-parameter mutation tool with full schema coverage and no output schema, the description covers purpose, timing, and the append default. Only the post-call effect (e.g., whether a scene identifier is returned) is unstated, which is minor.

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 100% and the description's only parameter remark ("position is 1-based; omit to append") restates the schema's own wording. It adds nothing about narration limits or video_id sourcing that the schema doesn't already carry, so baseline 3 applies.

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 gives a specific verb and resource ("Add a scene") and scopes it to the script-review phase with its narration. It implies the boundary against edit_scene/regenerate_scene by limiting itself to pre-approval, but never names a sibling tool explicitly.

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 states a concrete usage window — during script review, before approve_script — which is exactly the condition an agent needs to pick this over edit_scene. It stops short of explicit exclusions (e.g., what to use once the script is approved).

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