plan

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

With no annotations, the description carries the full behavioral burden and does disclose the critical non-mutating behavior. It also explains the kinds of changes included in the plan, though it lacks operational caveats such as whether the plan is scoped to a current collection or how duplicates are determined.

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 front-loaded with the key distinction that nothing is written, followed by a compact enumeration of plan categories. It is a single dense sentence with no filler, though the nested 'either ... or ...' clause could be easier to parse if split.

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 zero parameters and an existing output schema, the description supplies enough context to understand what the plan contains and that it is non-mutating. It could be more complete by clarifying the relationship to apply or the scope of the current collection.

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?

The tool takes zero parameters, so there is no parameter semantics to explain. The baseline of 4 applies because the description does not need to compensate for an input schema gap.

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 a dry-run planning function: 'What a run would change, writing nothing,' and enumerates the categories of planned changes. It distinguishes itself from a mutating run by saying nothing is written, but it does not explicitly name the sibling apply tool for contrast.

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 phrase 'writing nothing' implies this is a preview step before apply, but the description never explicitly says when to use this versus apply, purge, or status. It also omits prerequisites or exclusions, leaving usage to be inferred from the sibling names.

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