mcp_engram_relate

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

No annotations are provided, so the description carries full burden. It discloses the directional nature, the storage as a block, the use of VSA OP_BIND, and the requirement that concepts exist. However, it does not mention duplicate handling, error behavior if concepts do not exist, or potential side effects. Overall, it covers the main behavior well but lacks some edge-case transparency.

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 structured into two core sentences plus a usage guideline line, which is efficient and front-loaded. Some redundancy exists between the first two sentences (both mention directionality), but overall it is concise and well-organized. Minor tightening could improve clarity further.

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 simple parameter set (three strings) and no output schema, the description provides sufficient context: purpose, usage scenario, prerequisites, example labels, and references to related tools. It does not explain verification after creation or error handling for duplicates, but for a straightforward creation tool, this is fairly complete.

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?

All three parameters are described in the input schema with clear labels ('Source concept', 'Target concept', 'Relation label'), achieving 100% coverage. The description adds extra context like example labels and the directional arrow notation, but these largely duplicate the schema's example. Since schema coverage is high, baseline is 3, and the description adds only marginal value beyond the schema.

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 action ('Create a directional knowledge graph edge'), the resource (concepts), and the mechanism ('VSA OP_BIND', 'ZEDOS_RELATION block'). It also distinguishes from siblings by mentioning related tools like mcp_engram_search_by_relation and mcp_engram_visualize, which are for traversal and visualization respectively, making the purpose unique and well-defined.

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 includes an explicit 'WHEN TO USE' section that lists example relation labels and indicates when to apply the tool. It also states a precondition ('Both concepts must already exist in memory before relating them') and references alternative tools for related tasks (traverse with search_by_relation, visualize with visualize), providing clear guidance on when to use this tool versus others.

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