Configure executor functions, custom commands and size

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: writes are validated against the assigned class, locked targets are refused up-front (the console silently ignores writes), unlock applies changes then relocks even after failure, first set failure aborts the rest, read-backs must match, unreadable values are treated as unknown rather than defaulted, and mutations are serialised but not isolated from other clients. Shrink-before-growth ordering and pre-write collision checks are exactly the kind of non-obvious behavior an agent needs.

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 purpose and the primary alternative are front-loaded, and every sentence carries substantive constraints. However, the block is extremely dense and several sentences chain multiple rules with semicolons (lock/preview/verify/failure handling), making it harder to scan than a short bulleted structure would be.

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 22-parameter mutation tool with no output schema, the description covers what an agent must know: preview returns planned from -> to changes, verify defaults true and reads back, playback state is reported as activeBefore/activeAfter, unchanged values are never sent, and refusal conditions (page lock, collisions, footprint expansion, unknown dependencies) are enumerated. Return-value behavior is described even though no output schema exists.

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%, so the baseline is 3, but the description adds cross-parameter meaning the schema cannot express: encoder continuous functions vs discrete custom commands are mutually exclusive and conflicting requests fail before reads, custom command text is stored but never executed and requires explicit enabled because the console auto-enables it, and edge whitespace is refused because object reads trim it. This goes meaningfully beyond the per-field schema descriptions.

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 opening sentence names a specific verb (Set), the exact resources (key/MA-key/fader/encoder functions, custom command triplets, Width/Height, Fix), the target (Sequence or Macro executor at Page <p>.<e>) and the mechanism (writing properties). It also distinguishes itself from 'Assign <function> At' in the same breath, so an agent can select it without ambiguity.

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?

Explicitly routes the agent elsewhere: sequence-level settings (Wrap Around, priority) belong to gma3_configure_sequence, and the difference from 'Assign <function> At' is spelled out. It also states what this tool will never do (send Go/On/Off/Toggle/Flash, touch selection, programmer or fader levels), which is a clear when-not-to-use boundary.

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