capcut_add_subtitles

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose meaningful traits: dry-run by default, re-chunking behavior, and that punch words get their own card. However it omits that writing requires CapCut to be closed (that detail lives only in the schema), the mutation/reversibility profile, and what the dry-run actually returns.

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?

Three dense sentences that front-load the core action before detailing the optional re-chunking and positioning. The parentheticals about max_words/max_chars and split_by earn their place by clarifying behavior. Slightly packed but no wasted sentences.

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 16-parameter mutation tool with no annotations and no output schema, the description covers the primary features (SRT import, re-chunking, caps, punch cards, positioning, dry-run default). It leaves color, font_size, y, track, offset_s and min_gap_s to the schema, and says nothing about return values, but the safety-relevant default is surfaced.

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?

With 75% schema coverage the baseline is 3, but the description adds real meaning for the trickiest parameters: max_words/max_chars re-chunking, split_by ('time shared by letters or words on the frame grid'), upper (ALL CAPS), punch_words, and the x centring convention. This goes beyond the schema on the semantics that matter most for calling it correctly.

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 opens with a specific verb+resource: 'Import an SRT file (or SRT text) as caption text segments on one track.' That is far more than a restatement of the name. It references capcut_add_text for coordinate semantics, giving partial sibling differentiation, but does not explicitly distinguish itself from other text tools such as capcut_style_text or capcut_copy_text_template.

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?

Usage is implied by the import framing and the note that dry-run is the default, but there is no explicit when-to-use/when-not guidance or named alternative (e.g. use capcut_add_text for free-form text instead of an SRT). The agent must infer routing from the resource being an SRT file.

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