Create or overwrite a named macro from an ordered array of tool calls and parameters, enabling repeatable multi-step desktop actions in one command.
Create a new macro or overwrite an existing one. Steps are an array of {tool, params?} objects.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Macro name (lowercase, no spaces) | |
| steps | Yes | Array of steps: [{tool: 'tool_name', params: {}}] | |
| description | No | What this macro does |
Changes observed during successful MCP inspections.
v2.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already state non-read-only, non-open-world, non-destructive, so the safety profile is largely covered. The description adds the meaningful behavioral detail that this is an upsert (naming an existing macro silently overwrites it), which annotations do not reveal. It says nothing about validation of step tool names, error behavior, or how the macro is later executed, so there is a mild tension with destructiveHint=false that a caller overwriting an existing macro would care about.
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 action verb, zero filler. The overwrite semantics and the steps structure are both stated in the minimum space required.
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 3-parameter write tool with no output schema, the description omits what happens on an invalid step tool name, whether the call returns the created macro, and how the macro is subsequently invoked (run_macro). Adequate but with clear gaps for an agent composing macros programmatically.
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 100% and every parameter (name, steps, description) is documented in the schema, including the nested step shape. The description restates the steps array shape with the optional 'params?' marker, which adds only marginal clarification over what the schema already says.
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 pair (create/overwrite) and resource (macro), and adds the structural fact that a macro is a list of {tool, params?} steps. That is enough to separate it from run_macro/get_macro/list_macros, although it never names those siblings explicitly.
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?
Implied usage only: you call this to author a macro. There is no explicit guidance on when to use it versus run_macro or get_macro, and no warning about checking existing macros before overwriting one.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.