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

Beyond the annotations' destructiveHint, the description reveals that deletion cascades to every input row bearing the dataset_id, which is a material side effect. It also discloses a guard (refusal to delete the default Layer) and an auth constraint (unavailable to read-only keys), all of which are behavioral traits an agent could not infer from the schema or annotations.

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 short sentences, each carrying distinct information: the core destructive behavior, the default-layer safety guard, and the API-key restriction. The primary action is front-loaded and there is no filler.

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?

For a destructive operation with no output schema, the description covers what is deleted, the condition under which deletion is refused, and who is allowed to call it. The only missing details (e.g., irreversibility) are already signaled by destructiveHint=true.

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 schema gives no description for the required dataset_id parameter, but the description clarifies its role: it identifies the Layer and the input rows that will be deleted. summary and model_id are already described in the schema, so the description's partial parameter coverage is sufficient.

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 identifies a specific action ('Delete a Layer') and its precise scope ('every input row that carries its dataset_id'), and differentiates from the many sibling tools by naming a destructive delete operation rather than an update, import, or list. The guard about the default Layer and the auth restriction further pin down what this tool does.

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 gives clear context: use this tool to delete a Layer and its associated input rows, not to update or import a branch. It also states explicit when-not conditions—the default Layer is protected and read-only API keys cannot perform the operation—but it never names an alternative tool.

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