Run (Go+) or stop (Off) a macro and observe 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: it discloses that the call mutates state (sends Go+/Off), that observation polls over observe_seconds (default 3, max 60), the four possible run states, the dialog readback with bridge 0.42.0 dependency and "unknown" fallback, and the crucial caveat that dispatched does not mean every line succeeded. That is exactly the kind of side-effect and result-semantics detail annotations would otherwise supply.

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 EXECUTES/OBSERVES framing is front-loaded and every clause carries information. It is a dense single paragraph with stacked parentheticals (e.g. the MA Show Start wizard aside) that slow parsing, but there is little genuinely wasted text.

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 5-parameter, unannotated, no-output-schema mutation tool, the description covers side effects, timing, state vocabulary, dialog handling, and the dispatched-vs-observed distinction. The remaining gap is the return payload's full field list and the unexplained interval_ms, which keeps it short of complete.

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 20%, so the description has to compensate and it partially does: it defines action (go/off), macro N, and observe_seconds (default 3, max 60). However, interval_ms is never explained anywhere — its unit, default, and effect on polling are left to inference — and data_pool is only covered by the schema itself.

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?

"EXECUTES: action go sends Go+ Macro N ... off sends Off Macro N" names a specific verb (run/stop) and resource (macro N), then adds the observation behavior. It is clearly distinguishable from siblings like gma3_macros (listing), gma3_store_macro, and gma3_edit_macro_line, which an agent could otherwise confuse with it.

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?

It explains the two action modes and states the observation happens server-side "no Lua loop needed," implicitly steering the agent away from gma3_lua polling, and it explicitly routes dialog answering to gma3_dialog. It does not state when to prefer this over gma3_command or gma3_playback, so the alternative-selection guidance is clear but not exhaustive.

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