Skip to main content
Glama

Get Filings

get_filings
Read-onlyIdempotent

Retrieve filing history for a UK company by company_number (from search_companies). Returns up to 25 filings per page — each with category, type, description, filing date, action date, transaction ID, page count, and document metadata URL. Filter by category (accounts | confirmation-statement | officers | etc.).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryNoOptional filter (accounts | confirmation-statement | officers | etc.)
start_indexNoPagination offset (default 0)
company_numberYesUK company number (e.g. "07098618") OR the company NAME (e.g. "Ocado Group") — a name is resolved here automatically and the match is echoed back as resolved_from_name. Pass whichever you have; do not guess a number from memory, since a plausible wrong one returns a clean empty result that reads as "nothing filed" for a company that may not exist.
items_per_pageNo1-100 (default 25)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
totalYesTotal number of filings
filingsYesList of filing history records
company_numberYesUK company number
resolved_from_nameNoPresent only when a NAME was passed instead of a number. Shows which company answered, so a caller can see the resolution rather than assume it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / company_number / description
      Previous value: -"UK company number"New value: +"UK company number (e.g. \"07098618\") OR the company NAME (e.g. \"Ocado Group\") — a name is resolved here automatically and the match is echoed back as resolved_from_name. Pass whichever you have; do not guess a number from memory, since a plausible wrong one returns a clean empty result that reads as \"nothing filed\" for a company that may not exist."
    • addedOutput schema / properties / resolved_from_name
      Added value: +{
      +  "description": "Present only when a NAME was passed instead of a number. Shows which company answered, so a caller can see the resolution rather than assume it.",
      +  "properties": {
      +    "company_name": {
      +      "description": "Official name of the matched company.",
      +      "type": "string"
      +    },
      +    "company_number": {
      +      "description": "The number it resolved to.",
      +      "type": "string"
      +    },
      +    "resolved_from": {
      +      "description": "The name the caller passed.",
      +      "type": "string"
      +    },
      +    "status": {
      +      "description": "Company status; an active match is preferred over a dissolved namesake.",
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "company_number": "00006245"
      +  },
      +  {
      +    "category": "accounts",
      +    "company_number": "00006245",
      +    "items_per_page": 25
      +  }
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "company_number": {
      +      "description": "UK company number",
      +      "type": "string"
      +    },
      +    "filings": {
      +      "description": "List of filing history records",
      +      "items": {
      +        "properties": {
      +          "action_date": {
      +            "description": "Action date (ISO format)",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "category": {
      +            "description": "Filing category (accounts, confirmation-statement, etc.)",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "description": {
      +            "description": "Filing description",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "document_metadata": {
      +            "description": "Link to document metadata",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "filed_on": {
      +            "description": "Filing date (ISO format)",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "pages": {
      +            "description": "Number of pages in filing",
      +            "type": [
      +              "number",
      +              "null"
      +            ]
      +          },
      +          "transaction_id": {
      +            "description": "Filing transaction ID",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "type": {
      +            "description": "Filing type",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "total": {
      +      "description": "Total number of filings",
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "company_number",
      +    "total",
      +    "filings"
      +  ],
      +  "type": "object"
      +}
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds useful behavioral details such as 'Returns up to 25 filings per page' and lists the returned fields, plus the category filter. It does not contradict annotations and provides value beyond them.

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?

The description is two sentences, front-loaded with the primary purpose and then succinctly covering return fields and filtering. No filler or redundancy, earning a perfect score for efficiency.

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

Completeness4/5

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

With a rich output schema, complete parameter descriptions, and strong annotations, the description is largely complete. It covers return fields and filtering but does not mention pagination behavior (start_index) or the name-resolution nuance, though these are present in the schema. Overall, it is adequate for the tool's complexity.

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 the baseline is 3. The description mentions filter by category and company_number from search_companies, but the schema already provides detailed descriptions for all parameters, including the company_number resolution nuance. The description adds only marginal semantic value over the schema.

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?

The description clearly states the verb 'Retrieve' and the resource 'filing history for a UK company', explicitly linking to search_companies for obtaining the company_number. This distinguishes it from sibling tools like get_officers or get_company, making the purpose unambiguous.

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?

The description provides clear context by referencing 'from search_companies' and describing the filter categories, which implies when to use this tool. It does not explicitly exclude alternatives or state 'use when you need filings', but the context is strong enough for an agent to infer the appropriate use case.

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.