Apply a previewed change

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

The description goes beyond the annotations (readOnlyHint=false, destructiveHint=true) by detailing the dry_run default, the config override that can force dry_run, the two-phase apply refusal behavior, and the exact response fields to surface. This full transparency helps the agent understand potential non-committal behavior.

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 somewhat verbose with repeated warnings, but each paragraph conveys necessary safety-critical information (default behavior, config override, two-phase apply). The structure is logical and every sentence earns its place, though a slightly more compact phrasing could improve readability.

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?

The description is complete for a destructive tool: it covers the dry_run default, config overrides, two-phase apply behavior, response fields to surface, and the source of plan_id. Given the complexity and risk, nothing essential is missing.

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?

Even though the schema has 0% description coverage, the description fully explains both parameters: plan_id is described as coming from prior draft_* or pause/enable calls, and dry_run is explained in detail—its default value, how to override it, and the consequences. This completely compensates for the lack of schema-level 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 description clearly states the tool's purpose: 'Execute a previously previewed change.' It uses a specific verb and object, and distinguishes itself from sibling tools like draft_*, update_*, and pause/enable by focusing on applying an already-prepared plan.

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 description explicitly explains when to use the tool: after a prior draft_* or pause/enable call (since 'The plan_id comes from a prior draft_* or pause/enable tool call'). It also provides critical usage guidance about the dry_run parameter, including the need to pass dry_run=false to make real changes.

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