ae_executeCommand

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the mutation profile is partly covered. The description adds that the command applies to the current selection rather than an explicit target, which is real behavioral context. It does not disclose what happens on an unrecognized command string, whether the action is undoable, or how the 'ANY menu command' surface relates to the non-destructive annotation.

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?

Two sentences, front-loaded with the core capability and followed by the selection prerequisite. The parenthetical example list is slightly long but each example shows a distinct naming pattern (menu item, layer style, panel), so it earns its space.

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 catch-all command dispatcher with no output schema, the description covers what to pass and the selection dependency, but omits the return value and error behavior for invalid command names or ids. The 'ANY' framing also leaves the agent unsure which of the many sibling ae_* tools this duplicates.

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 67%: 'layers' and 'compositionName' are described in the schema, but 'command' is undocumented there. The description compensates by explaining that command accepts either a menu item name (with realistic examples) or a numeric id, which is meaningful added value. It says nothing about 'layers' or 'compositionName', leaving those entirely to the schema.

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 ANY menu command by name ... or numeric command id') and clarifies the host app is After Effects. However, the examples it lists ('Create Shapes from Vector Layer', 'Convert Audio to Keyframes') are exactly what dedicated siblings ae_shapesFromVector and ae_audioToKeyframes do, and the description never says when to prefer one over the other.

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?

It gives one concrete prerequisite — 'Acts on the current selection — use ae_selectLayers first' — which is genuinely useful sequencing guidance. But there is no statement of when to use this generic escape hatch versus the many dedicated ae_* tools, nor any note on exclusions or failure modes for unknown command names.

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