create_composition

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

With no annotations provided, the description carries full responsibility for behavioral transparency. It does not state whether this is a destructive action (e.g., overwriting existing comps), what side effects occur (e.g., timeline creation), or if the composition becomes the active one. The description is too brief to disclose any behavioral traits beyond the existence of creation.

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 with no fluff or repetition. It is appropriately front-loaded and immediately understandable. It earns its place, though it could benefit from slight expansion for clarity.

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?

Given the complexity of creating a composition (6 parameters, nested objects, no output schema), the description is inadequate. It does not explain what is returned (e.g., composition ID), the significance of the background color object, or any constraints like aspect ratio limits. An agent using this tool would need external knowledge to use it 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 100%, so the schema already documents all parameters and their types. The description adds no additional parameter context (e.g., valid ranges for width/height, pixel aspect ratio, or default behavior for backgroundColor). However, since the schema fully covers the parameters, the baseline score of 3 is appropriate—the description provides no extra value but doesn't hurt.

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 uses a standard verb-resource pattern ("Create a new composition"), which is clear and unambiguous. However, given the large sibling list with other creation tools like create_project and add_solid_layer, the description lacks any differentiation or scope detail (e.g., that composition is the primary container in After Effects). It is functional but minimally informative.

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 is provided on when to use this tool vs. alternatives. For example, compared to create_project or the various add_*_layer tools, there is no context for what a composition is or when composition creation is the right step. The description is purely declarative with no usage hints.

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