Compositions

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

With no annotations, the description carries the full burden. It provides one explicit behavioral warning about the volume of deep:true, which is useful. It does not disclose other side effects (e.g., delete being destructive, permission requirements, or that most actions mutate state). The single warning earns a 3, but richer disclosure would be needed for a higher score.

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 sentence plus a brief tip, efficiently listing operations and front-loading the primary purpose. It avoids redundancy and is appropriately sized for the scope of the tool. The structure is clean, though it could arguably be more explicit about parameter usage.

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 (30 parameters, 9 action enums, no output schema), the description is not fully complete. It does not describe the output format, parameter interactions, or default behaviors for actions beyond the schema. The deep:true warning adds useful context, but an agent might need to consult the schema heavily for correct invocation. It is adequate but with gaps.

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 coverage is 73%, so most parameters have descriptions in the schema. The description adds context for deep (detailed layer content) and warns about volume, but it does not explain many parameters like 'only', 'depth', 'clear', or the precedence between 'duration' and 'durationFrames'. The description adds marginal value beyond the schema, and the coverage is not high enough to rely solely on it, so a 3 is appropriate.

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 identifies the resource (compositions) and lists a range of operations (create, read, modify, duplicate, precompose, open, set markers, move playhead). It distinguishes itself from sibling tools by focusing on compositions, though it does not explicitly contrast with ae_layer or ae_property. The multi-action scope is clear but not a single specific verb, so it's a high 4.

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 specific usage tip for reading detailed content via deep:true with a volume warning, which helps avoid excessive output. However, it does not explicitly state when to use this tool versus alternatives like ae_layer for layer-level operations, or provide any exclusionary guidance. The guidance is implied but not comprehensive.

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