launcher_set_config

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

Annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false; the description usefully adds that input is validated before any write and that a preview summary is produced. What it does not disclose is what happens to the existing config that gets replaced, or whether the replacement can be undone — relevant since launcher_rollback and launcher_history exist as siblings.

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?

A single front-loaded sentence with no filler; the scope ('whole') leads and the behavioral caveats are parenthetical. It is efficient but almost too terse for a tool whose required argument is an unconstrained object.

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?

This is a configuration-replacing mutation with a nested open-ended required object and no output schema, so the description must carry most of the explanatory weight. It leaves undefined the config structure, the effect on the pre-existing layout, and the return shape after a successful write.

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 67%, but the uncovered 33% is the mandatory 'config' parameter — a free-form nested object with no description at all, and the description likewise never explains its shape or keys. The only semantic value added is the preview/validation framing for owner_approved, which is already stated in the schema. The required parameter is effectively undocumented everywhere.

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 gives a specific verb and resource: 'Replace the whole home-screen config'. 'Whole' distinguishes it by implication from the partial-mutation sibling launcher_edit, though that sibling is never named. An agent can tell what the tool does without opening the schema.

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 hints at a two-step workflow ('validated first; preview shows a summary'), which implies a preview-then-commit pattern, but the actual trigger (omitting owner_approved) lives only in the schema. It never says when to prefer this over launcher_edit, launcher_preview, or launcher_rollback when reverting.

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