Metis — KG Memory Connections

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

With no annotations, the description fully discloses the algorithm (BFS flood-fill from a starting entry up to depth hops) and the return format (entries grouped by distance with shared topics). It implies a read-only operation. While it omits performance characteristics or potential side effects, the provided details are sufficient for a query tool.

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 and well-structured: a one-sentence purpose, a sentence on the underlying graph and algorithm, then a bullet-point Args section. Every sentence adds value, and the critical purpose is front-loaded.

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 presence of an output schema and no annotations, the description covers the algorithm, all parameter semantics, and the return format (grouped by distance with shared topics). It is complete enough for a tool that traverses a memory graph, requiring no additional information.

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 description includes an Args section that explains the meaning and allowed values for entry_type ('memory', 'episodic', 'semantic', or 'idea'), entry_id, and depth (default 2). This adds crucial meaning beyond the schema, which only has names and types. With 0% schema description coverage, the description fully compensates.

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 finds memory entries connected via shared topics using BFS flood-fill. It identifies the starting entry and depth but does not explicitly differentiate from sibling tools like 'find_connections' or 'get_related_memories', though the algorithm mention (BFS, graph) provides implicit distinction.

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 implies usage context: when you need connected memories via shared topics, using the graph built by kg_index_memory(). However, it does not provide explicit guidance on when to use this tool over alternatives, nor does it mention prerequisites or exclusions.

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