Metis · Memory Curator — Get Related Memories

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

No annotations are present, so the description carries the full transparency burden. It mentions graph traversal ('Traverses the lightweight knowledge graph') but does not specify error handling (e.g., missing entry_id), performance characteristics, or confirm it is read-only. Adequate but not rich.

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?

Overall concise: two introductory sentences followed by a bullet-style parameter list. The structure front-loads the core purpose and usage. The parameter descriptions repeat some schema info but add value through explanation.

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?

For a tool with three parameters (two required, one optional) and an existing output schema, the description covers the core usage, parameter meanings, and a typical workflow link. It lacks details on error cases or edge conditions, but is sufficient for typical use.

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?

Input schema has 0% description coverage, so the description must compensate. The 'Args' section explains all three parameters: layer (memory type), entry_id (row ID), direction (outgoing/incoming/both with default). This adds meaningful context beyond the schema's bare type definitions.

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 it finds memories related to an entry via memory_relations using graph traversal. This distinguishes it from other memory tools like recall or search_memory, which focus on direct retrieval or text search, by highlighting the relational graph aspect.

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 advises using this after recall() and provides concrete examples (papers informed a decision, concepts relate to a workflow). Does not explicitly state when not to use, but the guidance is clear enough for typical scenarios.

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