Create a macro or replace or append its lines (never runs it)

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

With no annotations, the description carries the full burden and does so richly: it discloses the underlying command sequence (Store Macro N, Delete/Store Macro N.L, one set per property), reference checking before send, refusal on locked/running macros, and console text rewriting with read-back comparison and mismatch handling via accept_console_form.

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?

Content is dense and mostly earns its place, but it is delivered as one long semicolon-chained run-on paragraph that is hard to parse. It is front-loaded with 'mode' but the nesting of the lines array fields and behavioral caveats blurs structure.

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 complex 9-parameter tool with no output schema and no annotations, the description covers modes, line fields, verification, rewrite handling, and refusal conditions well. The main gaps are the unexplained 'verify' and 'preview' parameters and the implicit 'macro' identifier.

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 0% schema coverage the description must compensate, and it explains mode, the full lines array sub-fields (command, wait with 'follow'/'go', enabled, add_to_cmdline, execute, name, note, raw), name, note, cli, and accept_console_form. It leaves 'verify' and 'preview' unexplained and only indirectly references the 'macro' number via 'Store Macro N', so it is strong but not complete.

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 states a specific verb+resource (create/replace/append the lines of a macro) and explicitly clarifies scope with '(never runs it)' plus 'NEVER runs the macro', which cleanly distinguishes it from siblings like gma3_run_macro and gma3_edit_macro_line.

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?

Mode semantics function as implied usage guidance (create refuses an existing macro, replace removes lines first, append adds after), and it names a when-not condition ('Refuses a locked or running macro'). However, it never explicitly routes to alternative tools such as gma3_run_macro or gma3_edit_macro_line, so usage is only implied.

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