apply_plan

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

Adds substantial behavior beyond the annotations: backs up state, rejects drift, verifies writes by readback, stops on failure, never auto-replays, non-atomic multi-operation plans, and that the caller must inspect returned status rather than tool success. This is exactly the operational context a destructive, non-idempotent tool needs and goes well past the destructiveHint/openWorldHint flags.

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?

Four tight sentences, front-loaded with the action and timing constraint, followed by failure/verification semantics. No filler; each clause carries an operational fact.

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 a single-parameter apply tool with an output schema present, the description supplies the critical missing context: drift rejection, backup, readback verification, non-atomicity, and the instruction to read status. Nothing essential to correct invocation is absent.

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 0% for the single required plan_id, so the description must carry the load. It links the parameter implicitly to 'an authorized preview' that expires, which gives some semantics, but it never says where plan_id comes from (get_plan / plan_dns_batch) or its format.

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?

States a specific verb ('Execute') and resource ('an authorized preview', i.e. a previously created plan), which lets an agent separate it from get_plan (retrieval) and plan_dns_batch (creation). The phrasing 'execute an authorized preview' is slightly indirect about what is actually being applied, but the intent is recoverable.

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?

'before it expires' implies the tool is used on a preview that was authorized earlier, giving implicit ordering context. However, no sibling is named and there is no explicit when-not guidance (e.g. use plan_dns_batch first, or that this is the only path that mutates).

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