capcut_add_filter

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

The description discloses a key behavioral trait: the operation replaces any existing filter on the segment. This is important side-effect information that an agent needs to know. It also explains the intensity parameter's default behavior. With no annotations provided, the description carries the full burden, and it does a good job of disclosing the destructive replacement behavior. It could add more context about whether the operation is reversible or requires a saved draft, but the replacement warning is the most critical behavioral detail.

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 description is a single, dense sentence that front-loads the core action and then adds the two most important qualifiers: the filter source and the replacement behavior. Every word earns its place, and the intensity clarification is efficiently appended. No wasted words or redundant information.

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 tool with 4 parameters, no output schema, and no annotations, the description covers the essential context: what the tool does, where the filter comes from, the destructive replacement behavior, and the intensity semantics. The only minor gap is not explaining what 'draft' and 'segmentId' refer to, but those are inferable from the tool's purpose and sibling context. The description is complete enough for an agent to invoke the tool correctly.

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 0%, so the description must compensate. It explains that 'name' refers to a filter from capcut_list_filters, which is essential semantic context not in the schema. It also explains the 'intensity' parameter's range and default behavior. However, it doesn't explain 'draft' or 'segmentId' semantics, though those are fairly self-explanatory from their names and the tool's purpose. The description adds significant value for the two most ambiguous parameters.

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 states a specific verb ('Attach'), a specific resource ('a real CapCut filter'), and a clear scope ('to a segment'). It also distinguishes itself from other add tools by specifying the filter source (capcut_list_filters) and the replacement behavior. This clearly differentiates it from siblings like capcut_add_transition or capcut_add_mask.

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?

The description explicitly says to use a filter from capcut_list_filters, which is a clear usage guideline. It also states the replacement behavior ('replacing any filter already on it'), which tells the agent when this tool is appropriate. However, it doesn't explicitly say when NOT to use it or name alternatives for other operations, so it falls slightly short of a 5.

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