Preview operation

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

Annotations include readOnlyHint=true, and the description reinforces this by stating it creates a plan rather than performing the operation. It adds the behavioral detail that the plan is 'deterministic' and that no approval request is created. This goes beyond the annotation by clarifying the tool's side-effect-free nature, though it doesn't describe output format or failure modes.

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 single sentence with no fluff. It front-loads the primary action ('Create a deterministic safety preflight plan') and includes essential qualifiers ('for one write operation', 'without creating an approval request'). Every word earns its place.

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 complexity—12 parameters, 6 distinct operation types, and no output schema—the description is far too sparse. It doesn't explain what a 'safety preflight plan' contains, how to interpret it, or what parameters are required for different 'kind' values. This leaves the agent to guess at appropriate parameter selection and expected return values.

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 description coverage is 0%, and the description does not explain any of the 12 parameters. The schema provides names and types, but the description offers no guidance on how parameters map to the six 'kind' values or which combinations are required. For example, 'approval_wait_seconds' is not mentioned, and the relationship between 'project_id' and 'project_name' is unclear. The description fails to compensate for the lack of schema detail.

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 the tool's function: 'Create a deterministic safety preflight plan for one write operation.' It uses specific verb 'Create' with a specific resource (safety preflight plan) and scope (one write operation). It also distinguishes itself from approval-related tools by explicitly saying 'without creating an approval request,' which sets it apart from sibling tools like get_operation_approval and preview_service_execution.

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 description provides clear usage context: it is for previewing a single write operation before execution, and it explicitly notes what it does not do (create an approval request). While it doesn't name alternative tools, the context implies it should be used when a deterministic preflight check is needed without triggering approval.

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