add_memory

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

With no annotations provided, the description takes on full responsibility for behavioral disclosure. It clearly explains that by default the text is stored verbatim with no LLM call (offline, free), and that setting infer=true triggers LLM fact extraction. This goes beyond the schema by adding cost/offline context and a requirement. It does not mention return values or side effects, but the key behavioral traits are covered.

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 two sentences, each earning its place. The first states the core purpose, and the second explains the default vs. infer behavior. It is front-loaded with the primary action and contains zero fluff, making it exemplary in conciseness.

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 moderate complexity (5 parameters, no annotations, no output schema), the description covers the main action, default behavior, and a key option (infer) with its prerequisite. It does not explicitly state the return value, which would be helpful since there is no output schema, but the description is sufficiently complete for an agent to understand when and how to invoke the tool.

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?

The schema already covers 100% of parameters with meaningful descriptions, so a baseline of 3 applies. The description adds some context around the infer parameter (offline/free, requires configured LLM) but does not enrich the semantics of user_id, agent_id, or metadata beyond their schema descriptions. Overall, the added value is moderate.

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 opens with a clear verb+resource statement: 'Store a memory in the local OSS Mem0 store.' This immediately distinguishes it from sibling tools like search_memories, get_memories, update_memory, and delete_memory, establishing it as the creation tool. It also adds specificity about the default verbatim storage behavior, deepening the clarity.

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 explicit context for use: it is for storing a memory, with a clear distinction between the default offline/free mode and the LLM-based infer mode. It states a key prerequisite ('requires a configured LLM') for the infer option. However, it does not explicitly mention alternatives or when not to use the tool, so it lacks exclusions.

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