rlm_remember_if_novel

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

With no annotations, the description carries full burden. It discloses the core novelty-check behavior and return of duplicate matches when skipped. However, it omits details on side effects, permissions, error handling, and idempotency, leaving gaps in behavioral understanding.

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 with three sentences, front-loading the main purpose. It avoids unnecessary detail, though the second sentence on direct writes is slightly redundant given the schema.

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 13 parameters and no output schema or annotations, the description lacks information on return values for successful writes, failure modes, required dependencies (e.g., agent_id when scope=agent), and overall completeness for safe invocations.

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 54%, yet the description does not add meaning for individual parameters. It only restates the supported types ('fact, decision, learning...') already present in the schema enum, providing no additional constraint or usage context.

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's function: store a memory record only if it is sufficiently novel. It specifies the supported types and differentiates from siblings like rlm_remember and rlm_end_of_task_commit by emphasizing conditional storage.

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 provides guidance on when to use alternative tools ('Use context tools for source truth and rlm_end_of_task_commit for workflow capture'), implying when not to use this tool. However, it does not explicitly contrast with rlm_remember or rlm_remember_bulk for unconditional storage.

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