Detect numeric outliers using IQR and robust summary statistics, returning machine-readable anomaly positions. One successful call consumes 1 HumanMirror Forge credit.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Numeric series. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of behavioral disclosure. It does well by stating the algorithm family (IQR, robust summary statistics), the return kind (machine-readable anomaly positions), and a concrete cost constraint ('One successful call consumes 1 HumanMirror Forge credit'). It does not cover failure modes or edge cases, but the core behavior is 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 no filler: the method and output are front-loaded, and the credit-consumption note is relevant operational context. Every sentence earns its place.
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 single-parameter schema and no output schema, the description adequately covers what the tool does, how it does it, what it returns, and its cost. It could add explicit usage boundaries or edge-case behavior, but for this complexity level it is substantially 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?
The schema already has 100% coverage for the single 'input' parameter, describing it as 'Numeric series.' The description mostly reaffirms that the tool processes numeric series without adding parameter-specific constraints, formats, or examples, so the schema does the heavy lifting.
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 uses a specific verb ('Detect') and resource ('numeric outliers') and adds the method ('using IQR and robust summary statistics') plus the output type ('machine-readable anomaly positions'). This clearly distinguishes it from siblings like clean_json or score_data_quality.
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 intended use is implied by 'Detect numeric outliers' and the numeric series parameter, but there is no explicit guidance about when to choose this tool over alternatives or when not to use it. The description names no sibling tools or exclusion conditions.
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 targets a distinct data quality concern: JSON cleaning, record deduplication, numeric anomaly detection, entity normalization, and overall quality scoring. There is minimal overlap, and the descriptions clarify boundaries well.
All tool names follow a consistent verb_noun snake_case pattern (clean_json, dedupe_records, detect_anomaly, normalize_entity, score_data_quality). The naming is uniform and predictable, with only 'dedupe' being slightly informal but still clear.
Five tools is well-scoped for a data-quality-focused server. Each tool covers a meaningful operation without redundancy, and the count feels appropriate for the apparent purpose.
The surface covers the core data-quality lifecycle: cleaning, deduplication, anomaly detection, entity normalization, and scoring. Minor gaps exist such as explicit schema validation or date/number coercion, but the set is reasonably complete for common workflows.