plan_change

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

With no annotations provided, the description carries full behavioral burden. It adds useful context, such as PlanOptions fields being extracted before template args are passed, and the return fields (plan_id, plan_yaml, etc.). However, it does not explicitly disclose side effects or the lack thereof, such as whether the workspace is modified, which is important for a planning tool operating alongside execution siblings.

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 well-organized with an opening summary, Args section, and Returns section. It is appropriately concise and every section adds value, though the template-specific arguments list could be more complete without bloating this section.

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?

The description covers the two top-level parameters well and references the output schema's fields. However, the options object is open-ended and template-specific required args are only illustrated for one of four templates, leaving an agent to guess what to supply for audit, deploy, and dax_regression. This is a notable gap given the schema itself provides no help.

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 input schema provides no property descriptions (0% coverage), so the description must compensate—and it does. It explains intent as one of four templates and details options with a concrete safe_rename example, plus mentions PlanOptions extraction. This goes well beyond the bare schema, though it does not enumerate required args for the other three templates.

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 leads with a specific verb-resource pair: 'Create a versionable plan from a template name + structured args.' It names the four MVP templates and clarifies that this tool produces a plan rather than applying or auditing, distinguishing it from siblings like apply_plan and audit_model_and_report.

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 does not explicitly state when to use plan_change versus alternatives, such as 'use this before apply_plan' or 'use apply_plan to execute the generated plan.' The intent is implied by the word 'plan' but no direct usage guidance or exclusions are provided.

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