forget

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

The description discloses that data is removed from relational, graph, and vector databases, but does not mention irreversibility, permission requirements, or potential side effects. Since no annotations are provided, the description carries the burden and is somewhat lacking.

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 concise, front-loaded with the main action, and well-structured with a separate Parameters block. Every sentence adds value without redundancy.

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 adequately covers both usage modes and the effect on multiple databases. However, it does not address potential conflicts between parameters (e.g., if both are set) or error scenarios. Given the tool's simplicity, it is mostly complete.

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?

The description includes a detailed Parameters section that clarifies the meaning and usage of both parameters ('dataset' and 'everything'), which the input schema lacks. This adds significant value 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?

The description clearly states the tool deletes data from memory, distinguishing it from sibling tools like recall (retrieve) and remember (store). It specifies the action (delete) and the target (data from memory).

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 explains two usage modes: targeting a specific dataset or deleting all data. It does not explicitly state when not to use it or provide alternatives, but the context of sibling tools makes its unique role clear.

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