ExtendScript brut (dernier recours)

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

With no annotations, the description carries the full burden, and it discloses important behavior: execution within an undo group, access to 'app' and AEMCP utilities, and that the last evaluated expression is returned as JSON-serializable data. It does not explicitly mention potential side effects or read-only guarantees, but the 'arbitrary code' framing implies both possibilities, and the undo group hint adds context.

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 few sentences, front-loads the core purpose and usage constraint, and provides necessary context (access to app/AEMCP, return format) without clutter. It could trim minor redundancy but is appropriately concise for a powerful tool.

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 high complexity of arbitrary code execution, the description covers key aspects: the execution context, the undo group, available APIs, and return value contract. It lacks explicit error-handling notes, but that is often implied for eval tools. No output schema exists, so the return-type note is valuable.

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 only 33%, so the description must compensate. It explains the 'code' parameter with an example and indirectly hints at 'undoGroup' by mentioning the undo group, but 'timeoutMs' is left unexplained. The description adds some meaning to the code parameter but does not fully cover the undocumented parameters.

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 states a clear verb ('exécuter du code ExtendScript arbitraire') and resource (After Effects) and explicitly frames it as a last-resort tool distinct from siblings. It positions itself as the fallback when no other tool covers the need, which differentiates it clearly.

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 explicitly says 'A utiliser uniquement quand aucun autre outil ne couvre le besoin', giving a clear condition for when to use it. It doesn't name specific alternative tools, but the instruction to prefer other tools is unambiguous and sufficient guidance.

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