wave_set_appearance

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

No annotations are provided, so the description carries the full burden, and it does substantial work: it declares a persistent mutation to settings.json and discloses the confirm-before-write gate, which is the key behavioral trait. Gaps remain on permissions, whether a restart or reload is required for changes to take effect, and whether unspecified settings are preserved.

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?

Three sentences, front-loaded with the action and its blast radius, followed by the confirmation protocol, then the supported set. The key enumeration is the only mildly redundant part since the schema already lists them, but as a scannable capability summary it 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 an 11-parameter optional-field mutation with no annotations and no output schema, the description covers the essential unknowns: that it writes files, that it is gated by approved=true, and what is configurable. It stops short of describing merge-vs-replace semantics, validation failures, or whether the confirmation call echoes the proposed changes.

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 100% and each property carries a description plus its underlying settings key (e.g. term:fontsize), so the schema already does the heavy lifting. The description's list of supported keys largely restates the schema property names without adding types, ranges, or defaults.

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 concrete verb and resource ("Update Wave Terminal window or terminal appearance settings") and adds a durable side-effect ("writes to settings.json"), which an agent can act on. It lists exactly which keys are mutable, separating it from the broader wave_set_setting, but it never names the sibling tools it competes with (wave_set_setting, wave_set_theme), so an agent must infer the boundary.

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 two-step protocol ("First call returns a confirmation; pass approved=true to execute") is real operational guidance that changes how the agent calls the tool and is the most valuable sentence here. What's missing is routing guidance: with wave_set_setting and wave_set_theme in the sibling set, there's no statement of when to prefer this tool over those.

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