Run GridCraft engine commands

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotency, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the $steps[N].field cross-step reference syntax, that live=true drives the open app, and that commands run sequentially with a save at the end. It does not, however, explain failure handling or exactly what is destroyed/overwritten.

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 action is front-loaded and nearly every clause carries information (command families, delegated tools, step-id convention, $steps reference, live mode). It is dense and runs long as essentially one sentence, which hurts scanability slightly, but there is little filler.

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 an 11-parameter composite runner with no output schema, the description conveys the core execution model (ordered steps, engine tool steps, source workbook options, save step, live mode) so an agent can call it correctly. Gaps remain around error handling, overwrite behavior, and the output_dir/output_path pairing, keeping it short of a full 5.

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 description coverage is only 36%, so the description must compensate. It does clarify live, sample, the steps/id model, and the $steps[N] reference syntax (which is not in the schema), but leaves name, overwrite, all_sheets, output_dir, output_path, and stop_on_error unaddressed. Partial compensation warrants the baseline 3.

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 GridCraft engine commands in order') and makes the batch/composite nature explicit by enumerating the command families (cell.*, home.*, etc.) and the engine tools it can delegate to. An agent can immediately distinguish this general-purpose executor from single-operation siblings like create_workbook or edit_workbook.

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 'Advanced:' prefix and the description of operating on a new/sample/opened workbook imply context, and mentioning that it saves afterward gives a hint of when to reach for it. However, it never explicitly says when to prefer this batch tool over the plain sibling tools (create_workbook, edit_workbook, read_workbook), leaving the choice to inference.

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