NOUZ MCP Server

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

No annotations are provided, so the description carries the full disclosure burden. While it mentions 'embeddings' indicating the algorithm type, it fails to state whether this is read-only, what the return format is, or potential side effects. 'Suggest' implies non-destructive behavior but this should be explicit.

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 single sentence is front-loaded with the action, but extreme brevity results in underspecification. Given the 0% schema coverage and lack of annotations, this length is insufficient to convey necessary context.

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?

With 2 undocumented parameters, no annotations, and no output schema, the description provides inadequate context. It does not explain the relationship to the embedding system or the nature of the suggestions returned.

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 0% and the description fails to compensate. It does not explain what 'path' refers to (file path? entity identifier?) or what 'top_n' controls (number of suggestions? ranking threshold?). Both parameters are completely undocumented.

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 states the basic action ('Suggest parents') and method ('based on embeddings'), but fails to distinguish from sibling tool 'get_parents' or clarify what 'parents' refers to in this domain (file system, knowledge graph, etc.). It meets minimum viability but lacks specificity for sibling differentiation.

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?

No guidance provided on when to use this versus 'get_parents' or other sibling tools. No prerequisites mentioned (e.g., whether embeddings must be pre-calculated via 'embed' or 'index_all').

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