forget

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so exceptionally well. It explicitly labels the operation 'Destructive', explains the relevance threshold in cosine similarity terms, describes the below-floor behavior, and warns that without a floor any query would delete the nearest neighbor however unrelated.

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 well-structured and front-loaded: a one-sentence summary, then a short behavioral/safety paragraph, then the Args block. Every sentence contributes either to the tool's purpose, its destructive edge cases, or parameter semantics. The slight redundancy between the first sentence and the second paragraph is acceptable because it reinforces the safety-critical threshold behavior.

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?

For a destructive tool with no annotations, the description is remarkably complete. It covers the operation, the deletion condition, the edge case below the floor, the consequence of omitting the floor, and all three parameters with defaults. Since an output schema exists, the absence of detailed return-value docs is not a gap.

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, and it fully does. Each parameter gets a meaningful explanation: query describes the memory to remove, user_id defines the namespace with a default, and min_score is explained as a relevance floor with explicit guidance to lower it only when the reported candidate is confirmed.

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 verb and resource: 'Delete the single memory most relevant to `query`'. The qualifier 'if it is relevant enough' adds precision. However, it does not explicitly contrast this tool with recall, remember, or reset_memories, so sibling differentiation is implied by semantics 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 description gives contextual guidance about when deletion happens and cautions against lowering min_score until the candidate is confirmed. It also suggests sharpening the query when the floor is not met. But it does not explicitly tell an agent when to choose forget over recall, remember, or reset_memories, so the when-to-use advice is only partial.

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