Keyframes et courbes d'animation

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

With no annotations provided, the description carries the full behavioral burden. It explicitly discloses that After Effects influences and speeds are computed automatically, 'comme un reglage manuel de l'editeur de graphe' (like a manual graph editor adjustment), which is a meaningful behavioral trait. It also explains the semantics of the 'ease' field. However, it does not mention any destructive implications of 'delete' or 'clear', which would have warranted 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 compact and front-loaded: it states the core purpose in the first sentence, then elaborates on the key behavioral nuance. Every sentence earns its place, and there is no redundant filler. The structure is effective for quick parsing.

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 tool's complexity (12 parameters, 4 distinct actions), the description is somewhat thin on action-specific guidance. It does not explain what 'get' returns, what 'shift' requires (though the schema covers this), or potential error conditions. The coverage is adequate for a high-level understanding but incomplete for an agent that needs to handle all actions confidently without supplementary schema inspection.

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?

Although the schema covers all 12 parameters at 100% coverage, the description adds valuable context beyond the schema. It explains the 'ease' field's meaning and the available curve names (expo.out, back.out, etc.), and it clarifies path shortcuts like 'transform/position' and Adobe matchNames. This goes beyond simple schema repetition and helps agents understand the conceptual model.

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 clear, specific verb and resource: 'Poser, lire, supprimer et decaler des keyframes' (place, read, delete, and shift keyframes), and adds a distinctive qualifier 'avec de vraies courbes de vitesse' (with real speed curves). This immediately distinguishes the tool from siblings like ae_animate or ae_property, which handle broader animation or property tasks.

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 implies usage for keyframe manipulation but never explicitly states when to prefer this tool over alternatives, nor does it mention exclusions (e.g., 'use ae_animate for purely procedural animation'). The 'action' enum in the schema gives some context, but the description itself lacks direct guidance on tool selection.

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