rlm_remember_bulk

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

No annotations are provided, so the description carries full burden. It discloses batching for efficiency and durability, but lacks details on authentication requirements (e.g., agent_id when scope=agent), idempotency, error behavior, or side effects. The warning about source documents adds some behavioral context but insufficient for a mutation tool.

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?

Three sentences with no fluff. First sentence states purpose, second adds efficiency, third gives constraints and anti-guidance. Front-loaded and 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?

Given the rich schema and no output schema, the description covers purpose, constraints, and anti-patterns well. It could mention the return format (e.g., confirmation) but is largely complete for a store operation.

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 coverage is 100%, with all parameters described in the schema. The description adds no new semantics beyond the schema (e.g., it does not explain field meaning, but the schema already does). 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 tool stores multiple durable Memory V2 records in a single call, providing a specific verb and resource. It distinguishes from sibling rlm_remember (singular) and from context tools via the anti-guidance about source documents.

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?

Explicitly states max 50 memories per call and warns not to use for source documents, directing to context tools instead. This provides clear when-to-use and when-not-to-use guidance with alternatives.

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