memory_forget

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

No annotations exist, so the description carries the full burden. It transparently discloses that the tool only creates a pending proposal requiring human approval before deletion, which is the key behavioral trait. It does not elaborate on other aspects like idempotency or validation.

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 with no wasted words. The first sentence states the primary action and scope, and the second adds the critical behavioral note about pending approval. It is front-loaded and efficient.

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 8 parameters, 2 required, no output schema, and sibling tools for approval/rejection/list, the description is fairly complete. It explains the tool’s purpose and the proposal workflow. It could be improved by hinting at the return value (e.g., proposal ID), but overall adequate.

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 having a clear description. The tool description adds an overview of forgetting by id or scope/tags but does not provide additional meaning beyond what the schema already conveys.

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 proposes forgetting memories by id or scope/tags, and distinguishes it from direct deletion by noting it creates a pending proposal. This is a specific verb+resource pairing that differentiates it from siblings like memory_approve_forget.

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 provides clear context for when to use the tool (to initiate a forget proposal) and implies that actual deletion requires human approval. However, it does not explicitly name alternatives or state when not to use it, though the proposal nature is clear.

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