capcut_validate

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

The description discloses the categories of validation performed, which adds real behavior beyond the tool name. However, with no annotations, it does not explicitly state whether the tool is read-only, whether it can mutate the draft, or what happens when problems are found (returned report vs throw).

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?

A single 16-word sentence, front-loaded with the action and followed by a compact enumeration of checks. Every word adds information and there is no 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?

With no output schema or annotations, the description leaves unclear the return value (boolean vs list of issues), the exact meaning of the draft string, and error behavior. Completeness is low for an agent that must decide whether validation passed and how to interpret results.

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?

The schema only defines 'draft' as a required string with no description, so the burden falls on the description. It identifies the draft as 'in-session' but does not explain whether the string is a draft ID, serialized draft JSON, or a reference to a session object.

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 action ('check'), a specific object ('the in-session draft'), and enumerates the exact integrity dimensions checked (overlaps, duplicate ids/render_index, dangling references, missing media). This clearly distinguishes it from editing and inspection 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?

No guidance on when to call validation versus alternatives such as capcut_inspect_edit or capcut_read_timeline, and no mention of whether to run it before save or after edits. The only contextual hint is the parenthetical 'in-session,' which does not define selection criteria.

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