cyd_settings_set

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

With no annotations at all, the description carries the full burden, and it does disclose the most critical behavior: persistence semantics with merge-style updates (omitted settings unchanged). It does not disclose error behavior, whether changes apply immediately, persist across reboots, or require a device connection, but for a simple settings tool the merge semantics are the key behavioral trait and they are clearly stated.

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 description is compact and front-loaded: the core action and the partial-update caveat appear first, followed by the single parameter clarification that adds the most value. The "Action, L1" fragment is minor noise that adds no decision-relevant information, but overall every other sentence earns its place.

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 simple tool with four optional enum parameters and no output schema, the description covers scope, action, update semantics, and the ambiguous parameter. It falls short by not relating the tool to cyd_settings_get, not indicating what the tool returns after persisting (relevant since there is no output schema), and not stating whether settings survive reboots.

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 0%, so the description must compensate for four parameters. It explains keyboard_layout (the one genuinely ambiguous parameter, with jis/us enums) while the other three (theme, animation, brightness) have reasonably self-explanatory enum values. This is targeted compensation but does not fully describe all parameters; e.g., what distinguishes animation=fast from smooth is left unexplained.

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?

"Persist one or more settings" is a specific verb + resource statement that clearly identifies the tool as a write operation for settings. It is implicitly distinguished from the sibling cyd_settings_get through the set/get naming, though it does not explicitly name that sibling. Categorizing labels "Machine-specific (cyd)" and "Action, L1" add context about scope but do not sharpen the purpose.

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?

The statement "Omitted settings remain unchanged" communicates partial-update semantics, telling the agent it can safely modify a subset of settings without clobbering others. However, there is no explicit guidance about when to use this tool versus cyd_settings_get (read), cyd_radio_set (adjacent hardware settings), or other sibling tools, leaving routing largely implicit.

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