Apply Plan

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

Annotations already mark the tool as destructive. The description adds detailed behavior: execution order, stopping on first failure, individual snapshotting and journaling, and the two-step auth flow for non-admins. It also exposes the undo capability via journal IDs, going well beyond the annotations.

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 three sentences long, front-loaded with the core behavior. Each sentence adds necessary information: execution behavior, authentication requirement, and undo mechanism. No redundant or extraneous words.

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?

Given the tool's complexity and the presence of a detailed schema and annotations, the description covers key aspects: execution model, auth, and undo. It does not explain the structure of steps (handled by schema) or what happens after a failure (state might need clarification), but it mentions journal IDs for rollback, which implies the return value. Overall, it is sufficiently complete for an agent to use the tool correctly.

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 parameters routerId, steps, and confirmationToken are already described. The description adds meaning by explaining that confirmationToken is part of a two-step flow for non-admins, and that steps are journaled individually, which hints at the return of journal IDs (used in rollback). This improves upon the schema's own 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 executes write operations sequentially, stopping on failure, and distinguishes from siblings like plan_changes (which presumably creates the plan) and rollback_change (undo). The verb 'execute' paired with 'write operations in order' is specific and unambiguous.

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 provides guidance on when to use the tool: after obtaining a confirmationToken for non-admin identities, similar to other destructive tools. It also suggests using rollback_change for undoing steps. However, it does not explicitly state prerequisites (e.g., needing a plan from plan_changes) or when not to use it, but the sibling context implies this.

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