Create composition

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the description does not need to re-establish basic safety. It adds useful context beyond the annotations: the comp is empty, it opens in the viewer by default, names need not be unique, and the returned id should be used in later calls. It does not discuss failure modes or permissions, but with annotations covering the core safety profile this is a strong disclosure.

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 three dense sentences with no filler. The core creation behavior is front-loaded, followed by return-value guidance and then the sibling alternatives.

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?

There is no output schema, but the description explains exactly what is returned ('the new comp's id, name and settings') and how to use the id in subsequent calls. It also covers defaults, follow-up layer creation, and alternative tools for copying or precomposing, leaving no essential gap for correctly invoking or chaining this tool.

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 input schema already explains every parameter including defaults and ranges. The description adds only the name-non-uniqueness caveat and the id-return workflow, and does not elaborate on dimensions, duration, frame rate, or folder targeting beyond what the schema provides. The baseline of 3 is appropriate when the schema does the heavy lifting.

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 precise verb and resource: 'Create a new, empty composition in the open project', and immediately states the default viewer behavior. It clearly distinguishes creation from copying an existing comp or precomposing layers by naming ae_duplicate_comp and ae_precompose as alternatives.

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?

It gives explicit sequencing guidance ('Then add layers with ae_add_layer / ae_add_shape') and states when to use the alternatives: ae_duplicate_comp for copying an existing comp and ae_precompose for moving existing layers into a new comp. The default behavior and follow-up path leave little ambiguity about when and how to use this tool.

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