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

Annotations only declare readOnly=false, destructive=false and openWorld=false, so the description carries the real behavioral load and does so well: it discloses the pending-approval precondition, clarifies that picture generation is unaffected because each scene's image comes from its own idea, and states that the resulting card displays the full script. It does not say whether an edit invalidates a prior approval or how partial failures are handled.

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 edit capabilities are front-loaded in the first sentence and the enumeration maps directly onto the parameters. The trailing instruction about not pasting the script is meta-guidance rather than tool description, though it is short and operationally useful.

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?

Five parameters with a nested object array and no output schema, yet the description covers what can be changed, what remains unchanged (scene imagery), and what the caller will see afterwards (the full script on the card). That is enough for an agent to invoke it correctly without further documentation.

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 schema already explains lines, append, remove, opening and videoId; the description mostly restates those categories in prose. It adds one genuine clarification, that an appended sentence keeps the same picture, but nothing about how the parameters combine or whether they may be sent together. Baseline 3 is appropriate when the schema does the heavy lifting.

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 (changes the script of a draft) and then enumerates the concrete edit kinds: new words for given scenes, new words for the hook, scene removal, and a sentence appended to a scene. This distinguishes it cleanly from siblings such as suggest_line (which proposes text) and edit_video (which changes the video rather than the script).

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?

Gives a clear precondition for use: the draft must be 'waiting for the user's OK', which tells the agent this is a pre-approval edit. It also instructs the agent not to paste the resulting script into its reply. It stops short of naming alternatives when a draft is not pending approval (e.g. draft_video or suggest_line), so no explicit when-not routing.

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