forget_memory

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

No annotations are provided, so the description fully carries the burden. It discloses destructive behavior (permanent forget, cascade including KG triples and demotion), audit logging, and the confirm requirement for durable-tier memories. It does not mention error conditions or idempotency, but the key behavioral traits are covered.

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?

The description is two sentences, front-loaded with the core action and cascade, followed by usage guidance. Every sentence adds value without redundancy. It is optimally concise.

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?

The description covers the action, cascade effects, usage scenarios, and a key parameter constraint. It does not explain return values (no output schema) or prerequisites (e.g., memory existence). For a delete tool with cascade, this is adequate but not exhaustive.

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 100% with each parameter described. The description adds value by highlighting the confirm requirement for durable-tier memories, which is critical for correct invocation. The connection between reason and audit trail is implied. This goes beyond the schema baseline.

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 clearly states the tool performs a permanent forget with a full cascade (delete primary, remove KG triples, demote related memories, log audit trail). It distinguishes from sibling tools like store_memory or promote_memory by specifying the destructive and cascading nature. The usage context is explicitly provided.

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 specifies when to use: when a user explicitly requests forgetting or to clean up sensitive/incorrect data. It also notes the requirement for confirm=true on durable-tier memories. However, it does not explicitly state when not to use or compare to alternatives like a simple delete (which doesn't exist among siblings).

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