ai_runAction

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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety envelope is already structured data. The description contributes a non-obvious behavioral detail — that a .aia file can be loaded before playback — but omits what happens if the set/action is missing, whether the document is mutated, and what is returned.

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?

A single front-loaded sentence with no filler; the app scope comes first and the optional pre-step is attached where it belongs. Nothing could be removed without losing information.

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 three-parameter mutation-style tool with no output schema and lightly informative annotations, the description covers the core mechanic and the .aia option but not failure modes, document side effects, or result shape. Adequate to attempt a call, thin for predicting its effect.

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 0%, so all three parameters are bare strings with no documented meaning. The description clarifies that 'action' and 'set' are the action name and its set, and that loadAia is an .aia action file, but leaves open whether 'set' must be a pre-existing set, what format loadAia expects (path vs filename), and whether loading precedes or overrides existing actions.

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 — play a recorded action (name + set) inside Illustrator — and the app prefix distinguishes it from ps_runAction in the sibling list. It stops short of explicitly differentiating itself from ps_runAction or ps_actionManager, so it is clear but not sibling-aware.

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?

Use is only implied: an agent infers it should call this when an action needs to be played, and that loadAia is the route for a not-yet-installed .aia file. There is no explicit when-not guidance, no mention of ps_runAction as the Photoshop counterpart, and no stated prerequisite that the action set already exist in Illustrator.

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