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

Although annotations already declare destructiveHint=true and readOnlyHint=false, the description adds substantial value by specifying exactly what is deleted, the dependency conditions that block deletion, and the default preview behavior. This is strong behavioral disclosure beyond the 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 tightly packed sentences, front-loaded with the action and target, then dependency refusal, then preview behavior. Every sentence carries operational information.

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 undo tool with no output schema, this covers what is removed, what blocks the operation, and how to preview versus apply. Nothing essential for correct invocation is missing.

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%: runId is documented in the schema, while apply is not. The description compensates by explaining that apply=true performs the removal and omitting it previews, giving the undocumented parameter clear semantics. It adds little about runId beyond 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?

States a specific verb and resource: removes the deck written by a skew_grillage run. It enumerates exactly what is cleaned up (elements, nodes, structure groups, unused default properties), which clearly distinguishes it from the sibling skew_grillage run tool and other undo tools.

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?

Explains the key usage condition: it previews unless apply is true and refuses while dependent lanes, groups, or elements remain. It does not name an alternative tool for resolving dependencies, but the when-to-use and when-not-to-use conditions are clear.

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