rlm_memory_attach_source

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

With no annotations, the description partially covers behavior: it states it attaches evidence and accepts legacy IDs conditionally. However, it does not disclose side effects, whether it mutates records, error handling, or what happens if the migration map is missing.

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?

Extremely concise: two sentences convey the core purpose and a key constraint. No extraneous information, every word 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 description is too brief for a tool with 9 parameters and no output schema. It misses details about return values, how evidence is structured, and the overall effect on the memory record. Schema descriptions help but cannot fully compensate.

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%, so each param already has a description. The tool description adds the legacy ID context but does not provide additional meaning beyond the schema for individual parameters. Baseline of 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 attaches structured evidence to a Memory V2 record, including handling legacy IDs. This is a specific verb+resource that distinguishes it from sibling tools like rlm_remember or rlm_memory_supersede, though no explicit differentiation is provided.

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 on when to use this tool vs alternatives. It mentions a legacy ID condition but does not explain when to prefer this tool over other memory-related tools or what prerequisites (e.g., existence of migration map) are needed.

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