Calques

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. It mentions that list is lightweight and get with deep:true returns full detail, which implies performance characteristics. However, it does not disclose side effects of mutating actions like create, delete, or set, nor does it indicate whether operations require specific permissions, are reversible, or have any error states. For a tool with many destructive actions, this is a significant gap.

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 concise at two sentences, which is efficient for a tool with 64 parameters. It front-loads the main purpose and the key action hints. However, given the tool's complexity, the brevity borders on under-specification rather than effective conciseness; it does not use structure like bullet points or sections to organize the many capabilities.

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 no output schema, no annotations, and 64 parameters, the description is far from complete. It does not explain how to specify layers (by name, index, id, 'selected', 'all') even though the schema lists this, nor does it describe common behaviors like parent-child relationships, threeD, or time-based parameters. The tool is a comprehensive layer management tool, and a two-line description is inadequate for guiding an agent on correct invocation.

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 58%, so about 42% of parameters lack schema descriptions. The tool description adds minimal value beyond the schema: it mentions the action list and the deep flag behavior but does not explain key parameters like layer, comp, or the various create-specific properties. Since coverage is moderate, the description should compensate for undocumented parameters, but it fails to do so, leaving many parameters ambiguous.

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 tool creates, lists, reads, and modifies layers, with a specific list of layer types. It communicates the core purpose with a verb and resource. However, it does not differentiate from sibling tools like ae_shape, ae_mask, or ae_animate, which also deal with layer-related concepts, so the purpose is clear but not distinguished from 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?

The description gives a concrete usage hint: 'action=list est leger (a privilegier pour explorer)' recommending list for lightweight exploration, and 'action=get deep:true renvoie tout le detail' for full details. This provides some guidance on when to use specific actions, but it does not explain when to use this tool instead of sibling tools like ae_shape or ae_property, nor does it mention exclusions or prerequisites.

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