rlm_forget

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

With no annotations, the description must disclose behavioral traits. It only states that deletion occurs, but does not mention irreversibility, permissions needed, impact on related data, or rate limits. This is insufficient for an agent to understand the operation's side effects.

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 a single, direct sentence with no unnecessary words. It is front-loaded with the key action and resource.

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 four optional parameters and no output schema. The description does not explain how multiple filters combine (AND/OR), what the response indicates (e.g., number deleted), or any constraints. This leaves ambiguity for the agent.

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 75% (three of four parameters have descriptions). The description adds the ability to delete 'by ID or filter criteria', which provides context beyond the schema. However, it does not elaborate on parameter semantics further, so baseline 3 is appropriate.

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 action ('Delete') and the resource ('memories'), and specifies the method ('by ID or filter criteria'). This distinguishes it from siblings like rlm_remember (add) and other memory manipulation tools.

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?

No guidance is provided on when to use this tool versus alternatives such as rlm_memory_invalidate or rlm_memory_supersede. There is no mention of when to use or not use it, nor any prerequisites.

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