Run WordCraft engine commands

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

Annotations already declare destructive/non-idempotent, and the description adds real behavior: steps execute in order, step ids are tool names, parameters can reference prior step output via '$steps[N].field' (0-based), and live=true drives the app instead of a headless engine. It omits error/partial-failure semantics (stop_on_error) and overwrite behavior, which matter for a destructive batch 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?

Front-loaded with the core action, and the namespace enumeration earns its space by telling the agent which command prefixes exist. The trailing 'on a new document, a template or an opened file, then save' clause is slightly compressed to the point of ambiguity, but overall density is appropriate for a 16-param batch tool.

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 destructive, 16-param, no-output-schema batch executor the description covers execution order, step composition and live vs headless, but leaves saving/format/overwrite behavior, failure handling, and what is returned largely to the schema. Adequate, but an agent must still open the schema to know how output artifacts come back.

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?

At 63% schema coverage, the schema leaves 'steps' items essentially undocumented; the description compensates by explaining that step id is the tool name, ordering, and the $steps[N].field reference syntax, plus the live flag's meaning. It says nothing about template/open_path/formats interaction, but the core gap is covered.

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+resource ('run any of WordCraft's 615 engine commands in order') and enumerates the command namespaces and engine tools that can be used as steps. The 'Advanced:' framing and the inclusion of engine tool names (open_document, render_page, save_document) implicitly position it against siblings, but it never names a sibling tool directly.

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?

'Advanced:' signals this is an escape hatch, and the live=true sentence gives one mode-switch condition. However, there is no explicit 'use X instead for simple edits' or 'do not use when' guidance, despite many siblings (edit_document, convert_document, render_pages) covering subsets of this tool.

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