kernel_graph_scratch_drop

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

No annotations are supplied, so the description carries the full disclosure burden. It does convey the key trait that this is an irreversible wipe of caller-scoped ("your") state and that the data would expire at run end anyway, but it says nothing about recovery, error behavior if no scratch graph exists, or whether other agents are affected.

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?

A single short sentence with the destructive action front-loaded and the automatic-expiry caveat placed in a parenthetical. Nothing is wasted.

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?

An output schema exists, so return values need no explanation, and the zero-parameter shape keeps the surface small. For a destructive operation with no annotations, however, the description omits whether the wipe is scoped per-agent and what state becomes invalid afterward.

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 tool takes zero parameters, so no parameter documentation is required; the baseline for a parameterless schema applies.

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 uses a specific destructive verb ("Wipe") on a specific resource ("your scratch graph"), which is enough to distinguish it from the read-oriented sibling kernel_graph_scratch. It stops short of naming that sibling, so the differentiation is inferred rather than stated.

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 parenthetical "it also goes when your run ends" implies the tool is optional early cleanup rather than a required step, which is useful situational guidance. There is no explicit when-to-use vs when-not statement or named alternative for inspecting the scratch graph instead of dropping it.

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