search_knowledgeFinds what Nuira has been told about this business (facts, notes, suppliers, channels, products) by meaning, for questions phrased differently from how the knowledge was written. Use when get_business_profile does not obviously hold the answer. The similarity is a relevance score (higher is more relevant), not a business figure: never quote it as one.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavioral context: results carry a similarity relevance score that must never be quoted as a business figure. It doesn't mention the result cap or empty-result behavior, but that is minor against the annotations.
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?
Three tight sentences: what it does, when to use it, and a misuse warning front-loaded in each case. No repeated schema or annotation content.
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 2-parameter read-only tool with annotations and no output schema, the description covers purpose, routing, and return-score semantics. The remaining gap is practical invocation detail (what `limit` controls and its default) rather than conceptual understanding.
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%, so the description carries the full burden, and it never mentions either parameter. It conveys that `query` is free-text natural language via the semantic framing, but says nothing about `limit` (range 1-10) or the 2-300 character query bound.
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?
States a specific verb and resource: finds stored business knowledge (facts, notes, suppliers, channels, products) by meaning. It also scopes the operation to paraphrased questions, which no sibling tool does, so an agent can distinguish it from get_business_profile and the get_* family.
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?
Gives a clear trigger and names the alternative: 'Use when get_business_profile does not obviously hold the answer.' It doesn't cover the reverse case (when to prefer other siblings over this one, e.g. get_knowledge_coverage), but the primary routing decision is explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.