KB-grounded advisory threat classification for a piece of text. Returns the top-k matching threats with recommended controls. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | Number of threat matches to return (default 3) | |
| text | Yes | Text to classify against known threats |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Declares read-only and returns top-k threats with controls. No annotations provided, so description carries burden. Lacks details on performance, rate limits, or authentication.
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?
Two concise sentences covering purpose and output. No unnecessary words.
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?
Fully adequate for a simple tool with 2 parameters and no output schema. Read-only note and return value description suffice. Distinguishable from siblings.
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 coverage is 100% with descriptions for both parameters. Description adds little beyond schema: 'top-k' is hinted but not explicit. Baseline 3 is appropriate.
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?
Clearly states it is a KB-grounded threat classification tool for text, returning top-k threats with controls. 'Read-only' distinguishes from mutation tools. Siblings like kb_search and kb_checklist have different purposes, so this stands out.
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?
Implies usage for threat classification but gives no explicit when-to-use or when-not-to-use guidance. No mention of alternatives among siblings.
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.
Each tool has a distinct purpose: building checklists, classifying threats, mapping compliance, fetching by ID, listing entities, mapping framework IDs, traversing relationships, and semantic search. There is no overlap or ambiguity.
All tools use the 'kb_' prefix followed by a descriptive word, but the pattern varies: some are verbs (classify, get, list, search), one is a noun (checklist), and one is an adjective (related). Mostly consistent but with minor deviations.
8 tools is an appropriate number for a read-only knowledge base, covering the essential retrieval, search, and mapping operations without being excessive.
The tool set covers all necessary read operations for a security knowledge base: search, classification, compliance mapping, entity retrieval, listing, relationship traversal, and checklist generation. No obvious gaps given the read-only scope.