Explain whether a record fits the usual pattern for records like it, and which fields stand out. No Blueprint required.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | GeodesicAI API key (gai_...) | |
| blueprint | No | Discovery namespace used by discover_patterns | default |
| structured_data | Yes | The document's extracted fields as key/value pairs. Keys are open by design - your Blueprint's rules define what is checked |
Changes observed during successful MCP inspections.
Input schema / properties / blueprintAdded value: +{
+ "default": "default",
+ "description": "Discovery namespace used by discover_patterns",
+ "title": "Blueprint",
+ "type": "string"
+}Input schema / properties / api_key / descriptionAdded value: +"GeodesicAI API key (gai_...)"Input schema / properties / structured_data / descriptionAdded value: +"The document's extracted fields as key/value pairs. Keys are open by design - your Blueprint's rules define what is checked"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint, idempotentHint, and a non-destructive profile, so the safety behavior is covered. The description adds the meaningful behavioral detail that no Blueprint is required)Skip, but it does not explain what kind of output is returned or how the anomaly explanation is presented.
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 short sentences with no filler. The main purpose is front-loaded, and the optional blueprint caveat is placed at the end, making it easy to scan.
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 its simple explainer role and the strong safety annotations, the description is minimally viable. However, there is no output schema, and the description does not mention what the explanation looks like, how the 'usual pattern' is determined, or how the optional blueprint affects the analysis when one is supplied.
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 100%, so the baseline is 3; the description adds extra value by clarifying that structured_data is the record to analyze and that the blueprint is not a required prerequisite, beyond what the schema's default value implies. This helps an agent understand the relationship between the fields and the analysis.
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 a clear verb ('Explain') and a specific resource: whether a record fits the usual pattern and which fields stand out. It conveys the tool's analytical purpose, though it does not explicitly name or distinguish it from related sibling tools like discover_patterns or validate.
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 offers only the prerequisite note 'No Blueprint required,' which hints at a usage condition but gives no guidance on when to choose this tool over alternatives. It does not state when to use analyze_anomaly versus sibling tools such as validate, discover_patterns, or geometric_confidence.
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.