Skip to main content
Glama

Rank collection by a question

exim__collection__analyze
Read-onlyIdempotent

Ranks every company in a collection against a plain-language question, with a 0-100 score and one-sentence reasoning each.

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": {
      "collectionId": "<collectionId>",
      "question": "<question>"
    },
    "name": "exim__collection__analyze"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionYesPlain-language analytical question to rank against
collectionIdYesCollection name or id
rankingCriteriaNoOptional explicit weighting hints

Output Schema

NameRequiredDescriptionDefault
dataYes
statsNo
_debugNo
summaryYes
warningsNo
nextActionsYes
correlationIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / question / pattern
      Previous value: -"[^\\t\\n\\v\\f\\r\\x85\\p{Z}]"New value: +"[^\\t\\n\\v\\f\\r\\x85    - 

   ]"
    • addedOutput schema / $defs / value0 / properties / assessmentLabel
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / $defs / value0 / properties / modelInferred
      Added value: +{
      +  "type": "boolean"
      +}
    • changedOutput schema / $defs / value0 / required
      Previous value: -[
      -  "companyId",
      -  "companyName",
      -  "evidence",
      -  "rank",
      -  "reasoning",
      -  "score"
      -]New value: +[
      +  "assessmentLabel",
      +  "companyId",
      +  "companyName",
      +  "evidence",
      +  "modelInferred",
      +  "rank",
      +  "reasoning",
      +  "score"
      +]
    • changedOutput schema / $defs / value1 / required
      Previous value: -[
      -  "country",
      -  "description",
      -  "matchReasons",
      -  "tradePotential",
      -  "tradePotentialReasoning"
      -]New value: +[
      +  "country",
      +  "description",
      +  "matchReasons",
      +  "tradePotentialReasoning"
      +]
  2. Changed3 schema fields changed
    • addedOutput schema / properties / data / properties / context / anyOf
      Added value: +[
      +  {
      +    "type": [
      +      "null",
      +      "boolean",
      +      "number",
      +      "string",
      +      "array",
      +      "object"
      +    ]
      +  },
      +  {
      +    "additionalProperties": true,
      +    "properties": {
      +      "referenced": {
      +        "type": "boolean"
      +      },
      +      "rowCount": {
      +        "type": "integer"
      +      },
      +      "url": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "referenced",
      +      "rowCount",
      +      "url"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedOutput schema / properties / data / properties / context / type
      Removed value: -[
      -  "null",
      -  "boolean",
      -  "number",
      -  "string",
      -  "array",
      -  "object"
      -]
    • changedOutput schema / properties / data / properties / items / anyOf
      Previous value: -[
      -  {
      -    "items": {
      -      "$ref": "#/$defs/value0"
      -    },
      -    "type": "array"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "items": {
      +      "anyOf": [
      +        {
      +          "$ref": "#/$defs/value0"
      +        },
      +        {
      +          "additionalProperties": false,
      +          "properties": {
      +            "exportUrl": {
      +              "type": "string"
      +            },
      +            "payloadBytes": {
      +              "type": "integer"
      +            },
      +            "rowCount": {
      +              "type": "integer"
      +            },
      +            "token": {
      +              "type": "string"
      +            },
      +            "url": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "exportUrl",
      +            "payloadBytes",
      +            "rowCount",
      +            "token",
      +            "url"
      +          ],
      +          "type": "object"
      +        }
      +      ]
      +    },
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  3. Changed8 schema fields changed
    • removedInput schema / properties / --collectionId
      Removed value: -{
      -  "description": "Collection name or id",
      -  "type": "string"
      -}
    • removedInput schema / properties / --question
      Removed value: -{
      -  "description": "Plain-language analytical question to rank against",
      -  "pattern": "[^\\t\\n\\v\\f\\r\\x85\\p{Z}]",
      -  "type": "string"
      -}
    • removedInput schema / properties / --rankingCriteria
      Removed value: -{
      -  "description": "Optional explicit weighting hints",
      -  "type": "string"
      -}
    • addedInput schema / properties / collectionId
      Added value: +{
      +  "description": "Collection name or id",
      +  "maxLength": 8000,
      +  "type": "string"
      +}
    • addedInput schema / properties / question
      Added value: +{
      +  "description": "Plain-language analytical question to rank against",
      +  "maxLength": 8000,
      +  "pattern": "[^\\t\\n\\v\\f\\r\\x85\\p{Z}]",
      +  "type": "string"
      +}
    • addedInput schema / properties / rankingCriteria
      Added value: +{
      +  "description": "Optional explicit weighting hints",
      +  "maxLength": 8000,
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "--collectionId",
      -  "--question"
      -]New value: +[
      +  "collectionId",
      +  "question"
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$defs": {
      +    "value0": {
      +      "additionalProperties": false,
      +      "properties": {
      +        "companyId": {
      +          "type": "string"
      +        },
      +        "companyName": {
      +          "type": "string"
      +        },
      +        "evidence": {
      +          "$ref": "#/$defs/value1"
      +        },
      +        "rank": {
      +          "type": "integer"
      +        },
      +        "reasoning": {
      +          "type": "string"
      +        },
      +        "score": {
      +          "type": "integer"
      +        }
      +      },
      +      "required": [
      +        "companyId",
      +        "companyName",
      +        "evidence",
      +        "rank",
      +        "reasoning",
      +        "score"
      +      ],
      +      "type": "object"
      +    },
      +    "value1": {
      +      "additionalProperties": false,
      +      "properties": {
      +        "country": {
      +          "type": "string"
      +        },
      +        "description": {
      +          "type": "string"
      +        },
      +        "matchReasons": {
      +          "$ref": "#/$defs/value2"
      +        },
      +        "priority": {
      +          "anyOf": [
      +            {
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ]
      +        },
      +        "tradePotential": {
      +          "anyOf": [
      +            {
      +              "type": "number"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ]
      +        },
      +        "tradePotentialReasoning": {
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "country",
      +        "description",
      +        "matchReasons",
      +        "tradePotential",
      +        "tradePotentialReasoning"
      +      ],
      +      "type": "object"
      +    },
      +    "value2": {
      +      "anyOf": [
      +        {
      +          "items": {
      +            "type": "string"
      +          },
      +          "type": "array"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "value3": {
      +      "anyOf": [
      +        {
      +          "items": {
      +            "type": [
      +              "null",
      +              "boolean",
      +              "number",
      +              "string",
      +              "array",
      +              "object"
      +            ]
      +          },
      +          "type": "array"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "value4": {
      +      "anyOf": [
      +        {
      +          "items": {
      +            "$ref": "#/$defs/value5"
      +          },
      +          "type": "array"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "value5": {
      +      "additionalProperties": false,
      +      "properties": {
      +        "command": {
      +          "type": "string"
      +        },
      +        "cost": {
      +          "type": "string"
      +        },
      +        "label": {
      +          "type": "string"
      +        },
      +        "rationale": {
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "command",
      +        "cost",
      +        "label",
      +        "rationale"
      +      ],
      +      "type": "object"
      +    },
      +    "value6": {
      +      "anyOf": [
      +        {
      +          "additionalProperties": {
      +            "type": "number"
      +          },
      +          "type": "object"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "value7": {
      +      "anyOf": [
      +        {
      +          "items": {
      +            "$ref": "#/$defs/value8"
      +          },
      +          "type": "array"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "value8": {
      +      "additionalProperties": false,
      +      "properties": {
      +        "code": {
      +          "type": "string"
      +        },
      +        "message": {
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "code",
      +        "message"
      +      ],
      +      "type": "object"
      +    },
      +    "value9": {
      +      "anyOf": [
      +        {
      +          "additionalProperties": {
      +            "type": [
      +              "null",
      +              "boolean",
      +              "number",
      +              "string",
      +              "array",
      +              "object"
      +            ]
      +          },
      +          "type": "object"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    }
      +  },
      +  "additionalProperties": false,
      +  "properties": {
      +    "_debug": {
      +      "$ref": "#/$defs/value9"
      +    },
      +    "correlationId": {
      +      "type": "string"
      +    },
      +    "data": {
      +      "additionalProperties": false,
      +      "properties": {
      +        "context": {
      +          "type": [
      +            "null",
      +            "boolean",
      +            "number",
      +            "string",
      +            "array",
      +            "object"
      +          ]
      +        },
      +        "cursor": {
      +          "type": "string"
      +        },
      +        "has_more": {
      +          "type": "boolean"
      +        },
      +        "items": {
      +          "anyOf": [
      +            {
      +              "items": {
      +                "$ref": "#/$defs/value0"
      +              },
      +              "type": "array"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ]
      +        }
      +      },
      +      "required": [
      +        "context",
      +        "has_more",
      +        "items"
      +      ],
      +      "type": "object"
      +    },
      +    "nextActions": {
      +      "$ref": "#/$defs/value4"
      +    },
      +    "stats": {
      +      "$ref": "#/$defs/value6"
      +    },
      +    "summary": {
      +      "type": "string"
      +    },
      +    "warnings": {
      +      "$ref": "#/$defs/value7"
      +    }
      +  },
      +  "required": [
      +    "data",
      +    "nextActions",
      +    "summary"
      +  ],
      +  "type": "object"
      +}
  4. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds that scoring is 0-100 with per-company reasoning, but does not disclose cost/latency characteristics that matter for a tool that ranks 'every' company, nor any limits on collection size — the main behavioral risk here.

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

Conciseness4/5

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

A single tight sentence with the verb and scope front-loaded and no filler. It is appropriately sized, though the trailing detail about score format and reasoning overlaps with the existing output schema.

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

Completeness3/5

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

With annotations covering safety and an output schema covering return values, the remaining gaps are usage routing and operational context (scale, cost, whether ranking hits an LLM). Given this is an analytical ranking tool over an entire collection, those omissions leave the definition only adequate.

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 description coverage is 100%, so question, collectionId, and rankingCriteria are all documented in the schema. The description reinforces the question parameter's nature but says nothing about the optional rankingCriteria weighting hints, adding no meaning beyond the schema. Baseline 3 applies.

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

Purpose4/5

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

States a specific verb and resource ('Ranks every company in a collection') plus the driving input ('plain-language question'), which is enough to distinguish it from collection listing tools. It stops short of naming a sibling alternative, so the differentiation is implied by scope rather than stated.

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

Usage Guidelines3/5

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

The phrase 'against a plain-language question' implies this is for semantic/fuzzy ranking rather than deterministic sorting, but there is no explicit when-to-use or when-not-to-use guidance versus siblings like employees__rank or profile-match__rank. An agent must infer the selection rule.

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.