Try a change without making it

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial context they cannot convey: the run happens on a throwaway copy, refusals mirror the real refusal, successes do not persist, and any returned ids belong to the copy rather than the real workspace. These are precisely the behavioral traits an agent needs to interpret results safely.

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 with no filler; the mechanism is front-loaded, then the result semantics, then the sibling exclusions. Every sentence carries distinct information.

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?

With no output schema, the description carries the burden of explaining returns, and it does: it says what a refusal means, what a success means, and how to treat returned ids. Combined with the annotation profile and full schema coverage, an agent has everything needed to invoke and interpret this tool.

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% and both parameters are described, so the baseline is 3. The description goes slightly further by framing the arguments object as a pass-through ('as you would send them to it'), which clarifies that the nested object's shape depends on the named target tool rather than this schema.

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 states a precise verb and mechanism: name a tool and its arguments, and it runs against a throwaway copy of the workspace. It also explicitly distinguishes itself from run_action and update_sameway, so an agent can separate it from the other mutation-adjacent siblings without opening a schema.

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?

It gives both a positive usage condition (dry-run a change before committing) and explicit exclusions with the reason ('Not for run_action or update_sameway, which reach outside the workspace'). This is exactly the when/when-not/alternatives guidance the dimension rewards.

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