Pattern-based heuristic risk scoring for LLM responses (0-100). Detects linguistic signals such as contradictory assertions, unsourced claims, and uncertainty markers. Not a semantic hallucination detector.
| Name | Required | Description | Default |
|---|---|---|---|
| context | No | Reference context for grounding | |
| response | Yes | LLM response to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and discloses key behaviors: it is heuristic, pattern-based, outputs a 0-100 risk score, and detects specific linguistic signals. It also clearly states a limitation (not a semantic detector). It could mention caveats about heuristic accuracy or the role of the optional context parameter, but overall it is quite transparent.
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 two sentences with zero filler. It front-loads the core purpose and scale, then elaborates with detection signals and a clear boundary. Every sentence earns its place, making it appropriately sized and well-structured.
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 absence of an output schema and annotations, the description provides essential context: the output range, detection methodology, and a limitation note. The schema covers the parameters adequately. It lacks explicit comparison to sibling tools, but the tool is simple (2 parameters, 1 required) and the description is otherwise complete for its complexity.
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 input schema already provides 100% coverage of both parameters with clear descriptions: 'response' is the text to analyze, and 'context' is the reference grounding context. The tool description does not add any parameter semantics beyond the schema. Baseline of 3 is appropriate given the high schema coverage.
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's purpose with a specific verb ('risk scoring') and resource ('LLM responses'), including the 0-100 output scale. It differentiates itself from semantic hallucination detectors through an explicit negation, but does not name sibling tools like consistency_check or drift_detector for direct comparison. This is clear and scoped, but not fully distinguished from all siblings.
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 when pattern-based linguistic risk scoring is needed and explicitly excludes semantic hallucination detection, providing a when-not hint. However, it does not name alternative tools or explain when to use this over the listed siblings such as quality_validator or schema_enforcer. The guidance is implied rather than 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.
The tools are mostly distinct, but consistency_check and drift_detector both involve comparing responses, and quality_validator and schema_enforcer overlap on validation. The descriptions help clarify boundaries, especially for hallucination_scorer which is clearly unique.
Most names follow a noun_noun pattern (drift_detector, hallucination_scorer, quality_validator, schema_enforcer), but consistency_check deviates by using a verb as the second element. All are snake_case, so the overall style is recognizable but not perfectly uniform.
Five tools is well within the optimal range for a focused monitoring server. Each tool addresses a distinct quality aspect without unnecessary bloat or sparsity.
The toolset covers key monitoring dimensions: single-response quality, schema validation, hallucination risk, cross-response consistency, and time-based drift. Missing semantic hallucination detection is acknowledged as a limitation, but it's a minor gap given the scope.