adobe_runScript

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

The description advertises 'full scripting-DOM access to EVERYTHING the app exposes', which necessarily includes mutating and destructive operations, while annotations declare destructiveHint=false. That tension is unreconciled. It also omits any warning about untrusted code, process blocking, or what happens on timeout, which matters most for an arbitrary-code-execution tool.

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?

Dense but front-loaded: capability and scope come first, execution contract second. The parenthetical helper list is slightly noisy but each item is genuinely useful to a caller writing code.

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?

For a six-parameter, open-ended code-execution tool with no output schema and only partial annotation coverage, the definition covers the calling contract but not the failure contract — no timeout semantics, error surfacing, or serialization limits on the returned value. Adequate, but not complete for a tool this powerful.

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?

With schema coverage at only 33%, the description compensates well: it explains that `code` is a function body that must return a JSON-able value, that `args` is surfaced as ARGS, and that `file` triggers $.evalFile of a .jsx. It leaves `undoGroup`, `timeoutSec`, and their defaults/costs undocumented, which is the remaining gap.

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?

States a specific verb and resource — run raw ExtendScript inside a named host application — and enumerates exactly what DOM surfaces are reachable (AE app.project, Premiere QE, Photoshop Action Manager, Illustrator DOM, BridgeTalk). This is far more specific than siblings like ae_executeCommand or ps_runAction, and an agent can tell it apart immediately.

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 explains the mechanics of use (code-as-function-body, preloaded helpers, ARGS, or file for $.evalFile) but never states when to prefer this over the many dedicated siblings (ae_runScriptFile, ps_runAction, ai_runAction, xapp_bridgeTalk) or when to avoid it. Usage is implied rather than routed.

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