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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds real context beyond them: branchDepth is fixed by the saved graph, supported fields come from the recipe, a durable job is returned, and an immutable base revision plus idempotency key are mandatory. It does not state explicitly what prior model state gets destroyed, and the caller-driven idempotency-key behavior sits at odds with idempotentHint=false, though that hint refers to natural idempotency rather than the key mechanism.

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?

Three dense sentences, front-loaded with the action and the model being modified, then the constraints, then the return type. Every sentence carries information; nothing is padded.

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 an output schema present, the description need not explain the returned effective values, and it correctly points at inspection for them. Given the complex six-variant recipe schema and the destructive mutation, the description covers the critical operational constraints, though it omits explicit sibling routing.

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 only 20%, so the description must carry weight; it partially does by noting that recipe supplies the supported fields and that branchDepth is fixed, but projectId and generatePreview are never explained and the recipe's six template variants and field ranges are left entirely to the 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?

Specific verb+resource: 'Regenerate an existing saved ngPlant model using its authenticated native .ngp graph' clearly identifies the operation on a saved model, and 'existing saved' implicitly separates it from vegetation_create. The description is clear but never names or contrasts a sibling tool, so it falls short of the top band.

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 states prerequisites (an existing saved model, immutable base revision, idempotency key) but never says when to choose this over vegetation_create, vegetation_inspect, or vegetation_templates. Usage is implied by 'existing saved' rather than explicitly scoped.

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