add_keyframe

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description does not state whether the keyframe creation is idempotent, what happens if a keyframe already exists at the given time (overwrite vs add), whether the clip must be on a track with keyframing enabled for the parameter, or what time format is expected. It also doesn't explain whether the component must already exist on the clip or if this creates it. This lack of behavioral detail is a significant gap for an editing operation that could have side effects.

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 concise sentence that communicates the core purpose without fluff. It is front-loaded with the action verb and clearly identifies the target. It could arguably be more detailed, but for its brevity it does not waste words.

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 5 required parameters and no annotations or output schema, the description leaves important context unclear. It doesn't explain behavior like whether adding a keyframe at the same time overwrites an existing keyframe, whether the parameter must already have keyframing enabled, or what units/format the value uses beyond schema hints. The description is minimal and relies entirely on parameter names for meaning, offering no additional context about edge cases or expected usage patterns. For an operation with meaningful complexity (keyframes in animation), this is a real 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 description coverage is 100% – all 5 parameters have descriptions in the schema. The description adds minimal value beyond the schema: it clarifies that 'componentName' and 'paramName' refer to display names, which the schema already states. The description doesn't explain parameter semantics like value units, time format expectations, or the relationship between paramName and componentName, but the schema's coverage is strong so the description need not duplicate it. Baseline 3 is appropriate given the good schema coverage.

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 clearly states the action: 'Adds a keyframe to a clip component parameter at a specific time.' It identifies the verb (adds), the object (keyframe), and the target (clip component parameter at a specific time). It is specific enough to distinguish from siblings like remove_keyframe_range and set_value_at_time, though it doesn't explicitly mention keyframe interpolation or easing which might be set elsewhere.

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 gives a clear sense of what the tool does but provides no guidance on when to use it versus alternatives like set_clip_position, set_clip_scale, or set_value_at_time. There is no mention of prerequisites (e.g., the clip must have a component with the named parameter), what happens if the parameter doesn't exist, or how this differs from setting a property without keyframing. Context is implied by the name and description but not explicit.

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