rlm_memory_clean_candidates

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

The description highlights read-only behavior and non-mutation, but lacks details on grouping criteria, potential biases, or how results are ordered. With no annotations, more behavioral context (e.g., whether results are cached or computed live) would be beneficial.

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 sentence covering the essential points, but listing multiple candidate types ('noise, duplicates...') could be structured for readability. Still, it is efficiently concise.

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 no output schema and the presence of closely related siblings like rlm_memory_duplicate_candidates, the description lacks specificity on how this tool differs. It does not explain return format or ordering, nor provide usage context beyond 'cleanup candidates'.

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?

All three parameters are described in the schema with full coverage. The description does not add extra meaning beyond the schema, so a baseline score 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 tool is read-only and returns cleanup candidates such as noise, duplicates, stale memories, and anomalies. It specifies it does not mutate memory, effectively distinguishing it from mutation tools like rlm_memory_compact or rlm_memory_invalidate.

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 implies the tool is for inspecting cleanup candidates but does not explicitly state when to use it versus alternatives like rlm_memory_duplicate_candidates. No guidance on when not to use it or prerequisites is provided.

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