memory_auto_extract_cleanup

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

With no annotations provided, the description carries the behavioral disclosure burden. It explicitly warns that 'delete' removes rows and that 'mark_wrong' is the safer governance choice, and it frames the operation as preview-or-apply. This is meaningful behavioral disclosure beyond the bare schema, though it is light on details about consequences of mark_wrong.

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?

Two well-structured sentences deliver the essential purpose and safety guidance without filler. The key distinction between preview and apply is front-loaded, and the important preference for mark_wrong over delete is placed immediately after.

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?

Given the tool has no required parameters, safe defaults, and an output schema, the description is largely complete for correct invocation. It explains what the tool targets, how to act, and which action is safer. The only notable omission is a fuller explanation of what 'mark_wrong' does to the record, but this is not fatal for using the tool safely.

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 0%, so the description must compensate. It adds real meaning to the 'action' parameter by defining valid intentions ('mark_wrong' vs 'delete') and implies the dry_run/preview distinction. However, it does not describe the 'limit' parameter or explicitly map 'Preview or apply' to the dry_run boolean, leaving some semantics to inference.

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 states a specific verb ('Preview or apply cleanup') and a specific resource ('auto-extracted noise records that look like implementation explanations rather than real user memory'). This clearly distinguishes the tool from the broader memory management siblings by naming the exact kind of data it targets.

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 concrete guidance on how to invoke the tool safely: 'Prefer action=mark_wrong for safer governance; use delete only when you really want to remove rows.' It also conveys preview-vs-apply semantics. It does not explicitly name alternative sibling tools, but the usage context is clear.

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