Revise script

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

Beyond the annotations, it discloses the critical behavioral split: without revised_script it is a read returning the previous script and grounding; with it, the server persists a new row whose parent is the prior script rather than mutating in place — consistent with destructiveHint=false. It also preempts a likely misread of the mode enum by stating 'The agent performs rewriting; server-side BYO generation is not implemented.'

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?

Four tight sentences, front-loaded with the two-mode purpose, then sequencing, then mode semantics. No filler and no repetition of schema text.

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?

With no output schema, the description correctly states what the context path returns, but it does not say what the write path returns (e.g., the new script-version id). Given a nested-object parameter and a non-idempotent annotation, that is the one remaining gap.

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%, so baseline is 3; the description adds real meaning by explaining the conditional effect of revised_script (context vs. new persisted version) and clarifying that mode is only a provenance label. It stops short of describing revision_target or critique_findings beyond what their schema text already says.

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 ('Prepare revision context for an existing video script, or save its replacement as a linked new version') and explicitly separates itself from generate_script ('for a new draft'). An agent can distinguish this dual read/write revision tool from its siblings without opening any schema.

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 explicit sequencing ('Use after get_script or critique_against_corpus') and names the alternative for the adjacent intent ('use generate_script for a new draft'). The two operating modes are also gated by a clear condition: omit revised_script for context, supply it to persist.

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