Execute operation

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

Beyond the destructiveHint annotation, the description discloses key behaviors: arguments are validated before reaching AE, every call is wrapped in one undo group, and the response includes ambient context at zero extra round trips. It also warns against calling beginUndoGroup/endUndoGroup in eval.run code. This adds substantial context beyond the structured 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?

Though the description is longer than average, every sentence conveys essential information: purpose, usage guidance, undo behavior, response context, and example. It is well-structured and front-loaded with the core purpose, then expands into usage details without redundancy.

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 generic nature (executes any catalog operation) and lack of output schema, the description covers invocation, validation, batching, undo behavior, response contents, and includes an example. It is sufficiently complete for an agent to select and invoke the tool correctly, especially with sibling tool context.

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?

The schema already documents all three parameters with 100% coverage. The description adds value by explaining validation semantics ('Arguments are validated against the operation's declared parameters'), clarifying that args can be omitted for zero-param operations, and providing a concrete example with operation and args. This goes beyond what the schema alone provides.

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 clearly states the tool's function: 'Execute an atomic operation by name (from ae_catalog).' It distinguishes ae_do from sibling tools like ae_comp_info and ae_layer_info by positioning it as the generic executor for operations defined in the catalog, making the purpose specific and unambiguous.

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?

Provides explicit usage guidance: 'Have more than one operation to run? Wrap them in ONE batch.run instead of several ae_do calls' and notes that read/verify steps can ride in the same batch. It also clearly states when not to use ae_do (for undo/redo operations that cannot ride inside a batch.run).

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