forget

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

With no annotations, the description must disclose behavioral traits, but it fails to mention the confirm flag that gates execution or the reject mode that turns deletion into a non-destructive tombstone. The description simply says 'delete' without noting these important safeguards or behavioral nuances, leaving a significant transparency gap for a destructive operation.

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 only two sentences, with the first front-loading the purpose and the second adding a critical usage boundary. There is no redundancy, fluff, or wasted words; every sentence earns its place.

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 tool has a complex schema with nested filters, a confirmation flag, and a reject mode, yet the description provides almost no context about these behaviors. It does not explain the confirmation workflow, the difference between reject and delete, or how filtering operates. For a potentially destructive tool with no annotations and no output schema, this is significantly under-specified.

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 schema has 83% description coverage, so most parameters are already self-documenting. The description adds little beyond the schema: 'specific' hints at id/filter selection but does not clarify how to choose between id and filter, or how confirm and reject interact. This is a standard baseline score for high schema coverage.

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 states a specific verb and resource: 'Delete specific memory entries.' It is unambiguous and distinguishes the action from siblings like update or consolidate through the strong verb 'delete' and qualifier 'specific.' However, it does not explicitly mention alternative sibling tools, so it does not fully achieve the top score.

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 explicit when and when-not guidance: 'Use this tool only when the user requests a deletion' and 'Do not auto-forget.' This clearly sets the boundary for appropriate use. It does not name alternatives like update or reject, which the schema supports, so it stops short of full guidance.

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