MemOS

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It extensively documents critical behavioral traits: the mandatory auto-invocation protocol, the 'Four-Step Judgment' process for memory safety, the presence of AI speculations and noise in results, and the requirement to filter memories before use. It also specifies output constraints like not mentioning internal system terms. This provides comprehensive behavioral context beyond what a basic schema would offer.

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 excessively long (over 500 words) and includes extensive procedural instructions that belong in agent guidelines rather than a tool description. While well-structured with sections like 'Purpose', 'Usage requirements', 'Critical Protocol', and 'Parameters', it contains significant redundancy and over-specification that doesn't earn its place in a tool description. The core purpose and usage could be communicated in 20% of this length.

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 complexity of memory retrieval with safety protocols and no output schema, the description provides substantial context about what the tool does, how to use it, and how to handle results. It covers the retrieval purpose, mandatory invocation pattern, memory safety protocols, parameter usage, and result handling. The main gap is the lack of output schema documentation, but the description compensates by explaining how to process the returned memories.

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 100%, so the schema already documents all three parameters. The description adds some additional context about 'query' ('should be a concise summary of the current user message') and 'memory_limit_number' ('defaults to 20'), but these details are largely redundant with the schema. The description doesn't add significant semantic value beyond what the structured schema provides.

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 explicitly states the purpose as 'MemOS retrieval API. Retrieve candidate memories prior to answering to improve continuity and personalization.' This is a specific verb ('retrieve') + resource ('memories') combination that clearly distinguishes it from sibling tools like add_feedback, add_message, and delete_memory which perform different operations.

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 usage requirements: 'MUST be auto-invoked by the client before generating every answer (including greetings like "hello"). Do not wait for the user to request memory/MCP/tool usage.' It also specifies when to proceed without memories: 'If none are relevant, proceed to answer normally.' This gives clear guidance on when and how to use this tool versus alternatives.

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