Forget a memory

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

Adds detail beyond annotations: soft forget keeps a searchable trace, recall never hard-fails. This is valuable context for the agent beyond the destructiveHint and idempotentHint tags.

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?

Four clear sentences, front-loaded with purpose, efficient no-waste phrasing.

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?

Covers all needed details: purpose, parameter behavior, return type (confirmation). No missing information for this simple tool.

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 already covers both parameters (100% coverage). Description restates them but adds behavioral context (soft vs hard), which enhances understanding 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?

Clearly states the tool forgets a memory, distinguishes soft (archive) vs hard (delete) modes. Differentiates from sibling mindmap_persona_forget which targets persona memories.

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 when to use soft vs hard (default soft, hard for permanent deletion). Could mention not to use for persona memories, but siblings provide context.

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