Preview an operation before running it

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

Annotations indicate it is read-only, but the description adds crucial behavioral details beyond that: the plan must be shown to the user, explicit approval is required, the token is single-use, expires in a few minutes, and is invalidated if the planned operation changes. It does not repeat annotation content and adds necessary context about the confirmation flow.

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 a tight, front-loaded paragraph of three sentences that conveys all critical information without redundancy. Every sentence contributes to correct usage.

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 meta nature, no output schema, and the need to explain the confirmation workflow, the description covers purpose, parameters, expected actions, token behavior, and validation. It is complete for an agent to invoke it 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 50%, and the description clarifies that 'tool' should be the name of the write tool and 'arguments' should be the arguments without confirmationToken and requestId. This adds meaning beyond the enum and vague schema description, helping the agent construct correct calls.

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 specific verb and resource ('describe exactly what a confirmable write tool would do') and explains the output (a plan and a confirmationToken). It clearly distinguishes this meta-tool from the actual write tools it previews, making the purpose unmistakable.

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 tells the agent to use this tool before any confirmable write (passing the write tool name and arguments without confirmationToken and requestId), to show the plan to the user, and to wait for explicit yes before calling the write tool with the token. It also warns that the token is single-use, expires, and is refused if the plan changes, which fully guides usage.

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