Skip to main content
Glama

Compare screening runs

compare_screening_runs
Read-only

Compare two completed screens by their screeningId and see what changed. Costs zero credits. Two runs of the same address show why the reputation score moved. Two different addresses show a side by side. Returns each run score, band, and confidence, a reason level diff, and the score change broken into its drivers. Small differences between runs of one address can be normal variation rather than a data change.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "runIdA": "<runIdA>",
      "runIdB": "<runIdB>"
    },
    "name": "compare_screening_runs"
  }
}

Input Schema

NameRequiredDescriptionDefault
runIdAYesFirst screeningId (rsr_...). Must be a completed screen you own.
runIdBYesSecond screeningId (rsr_...). Must be a completed screen you own.

Output Schema

NameRequiredDescriptionDefault
modeYestemporal_delta when both runs are the same address, else side_by_side
runAYes
runBYes
reasonDiffYesWhat changed between the two runs at the reason level
scoreDeltaYesrunA score minus runB score
compositionDiffYesWhich score drivers differ between the runs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed22 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedOutput schema / properties / reasonDiff / properties / added / items / properties / severity / $ref
      Removed value: -"#/properties/runA/properties/confidence/anyOf/0"
    • addedOutput schema / properties / reasonDiff / properties / added / items / properties / severity / enum
      Added value: +[
      +  "High",
      +  "Medium",
      +  "Low"
      +]
    • addedOutput schema / properties / reasonDiff / properties / added / items / properties / severity / type
      Added value: +"string"
    • removedOutput schema / properties / reasonDiff / properties / changed / items / properties / from / $ref
      Removed value: -"#/properties/runA/properties/confidence/anyOf/0"
    • addedOutput schema / properties / reasonDiff / properties / changed / items / properties / from / enum
      Added value: +[
      +  "High",
      +  "Medium",
      +  "Low"
      +]
    • addedOutput schema / properties / reasonDiff / properties / changed / items / properties / from / type
      Added value: +"string"
    • removedOutput schema / properties / reasonDiff / properties / changed / items / properties / to / $ref
      Removed value: -"#/properties/runA/properties/confidence/anyOf/0"
    • addedOutput schema / properties / reasonDiff / properties / changed / items / properties / to / enum
      Added value: +[
      +  "High",
      +  "Medium",
      +  "Low"
      +]
    • addedOutput schema / properties / reasonDiff / properties / changed / items / properties / to / type
      Added value: +"string"
    • removedOutput schema / properties / reasonDiff / properties / removed / items / $ref
      Removed value: -"#/properties/reasonDiff/properties/added/items"
    • addedOutput schema / properties / reasonDiff / properties / removed / items / additionalProperties
      Added value: +false
    • addedOutput schema / properties / reasonDiff / properties / removed / items / properties
      Added value: +{
      +  "code": {
      +    "type": "string"
      +  },
      +  "factor": {
      +    "type": "string"
      +  },
      +  "message": {
      +    "type": "string"
      +  },
      +  "severity": {
      +    "enum": [
      +      "High",
      +      "Medium",
      +      "Low"
      +    ],
      +    "type": "string"
      +  }
      +}
    • addedOutput schema / properties / reasonDiff / properties / removed / items / required
      Added value: +[
      +  "code",
      +  "factor",
      +  "severity",
      +  "message"
      +]
    • addedOutput schema / properties / reasonDiff / properties / removed / items / type
      Added value: +"object"
    • addedOutput schema / properties / runA / properties / transactionCount / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / runA / properties / transactionCount / minimum
      Added value: +-9007199254740991
    • removedOutput schema / properties / runB / $ref
      Removed value: -"#/properties/runA"
    • addedOutput schema / properties / runB / additionalProperties
      Added value: +false
    • addedOutput schema / properties / runB / properties
      Added value: +{
      +  "address": {
      +    "description": "The screened address",
      +    "type": "string"
      +  },
      +  "band": {
      +    "description": "Reputation band, e.g. Low Risk",
      +    "type": "string"
      +  },
      +  "bandCode": {
      +    "description": "Band identifier, e.g. LOW_RISK",
      +    "type": "string"
      +  },
      +  "confidence": {
      +    "anyOf": [
      +      {
      +        "enum": [
      +          "High",
      +          "Medium",
      +          "Low"
      +        ],
      +        "type": "string"
      +      },
      +      {
      +        "type": "null"
      +      }
      +    ],
      +    "description": "Engine confidence for this run"
      +  },
      +  "ensName": {
      +    "description": "ENS name for the address, when known",
      +    "type": [
      +      "string",
      +      "null"
      +    ]
      +  },
      +  "reportUrl": {
      +    "description": "Link to the full report on the Probity dashboard",
      +    "type": "string"
      +  },
      +  "score": {
      +    "description": "Signed reputation score from -100 to +100. Lower is worse.",
      +    "type": "number"
      +  },
      +  "screenedAt": {
      +    "description": "When this screen ran (ISO-8601)",
      +    "type": "string"
      +  },
      +  "screeningId": {
      +    "description": "The rsr_... id of this run",
      +    "type": "string"
      +  },
      +  "transactionCount": {
      +    "description": "Number of transactions analysed",
      +    "maximum": 9007199254740991,
      +    "minimum": -9007199254740991,
      +    "type": "integer"
      +  }
      +}
    • addedOutput schema / properties / runB / required
      Added value: +[
      +  "screeningId",
      +  "address",
      +  "ensName",
      +  "score",
      +  "bandCode",
      +  "band",
      +  "confidence",
      +  "transactionCount",
      +  "screenedAt",
      +  "reportUrl"
      +]
    • addedOutput schema / properties / runB / type
      Added value: +"object"
  2. Changed2 schema fields changed
    • changedInput schema / properties / runIdA / description
      Previous value: -"First screeningId (rsr_...)"New value: +"First screeningId (rsr_...). Must be a completed screen you own."
    • changedInput schema / properties / runIdB / description
      Previous value: -"Second screeningId (rsr_...)"New value: +"Second screeningId (rsr_...). Must be a completed screen you own."
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark it read-only, but the description adds credit cost, detailed return contents, and a caveat that small differences may be normal variation. This supplies useful context beyond structured fields without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose, then packs cost, two use cases, return summary, and caveat into a compact paragraph. Every sentence adds information and no filler is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema and read-only annotations, the description still covers cost, use cases, return contents, and result interpretation. Nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both runIdA and runIdB fully described. The description mentions screeningId but adds no format, constraint, or meaning beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (compare) and resource (two completed screens by screeningId) and distinguishes same-address vs different-address scenarios. An agent can identify the operation and its scope without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear use cases: same address to diagnose score movement, different addresses for side-by-side comparison, and notes zero credit cost. Does not name alternative sibling tools or when not to use it, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources