Apply Plan

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

Annotations indicate destructive, not read-only. Description adds that execution stops on first failure, each step is snapshotted and journaled, and confirmation is required for non-admins, going beyond annotation details.

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?

Two sentences, no wasted words. First sentence explains core behavior, second provides complementary usage guidance. Information is front-loaded and efficient.

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 complexity (multi-step writes), annotations, and no output schema, the description covers failure handling, confirmation requirements, and undo path. Agent has sufficient context to invoke 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 covers all 3 parameters with descriptions. The description adds value by clarifying that steps are ordered and that dryRun is injected automatically, and confirmationToken's role in two-step authorization.

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?

Description clearly states 'Execute a sequence of write operations in order' and mentions stopping on first failure, distinguishing it from sibling tools like bulk_execute or rollback_change.

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?

Explicitly states when confirmationToken is needed (non-admin identities) and provides alternative (use rollback_change with journal IDs). Also references a two-step flow common to destructive tools.

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