Skip to main content
Glama

find-missing

by io.github.NKO-STUDIO

find_missing

Query whether an entity with a real LEI has a high-confidence match in the national commercial registry its declared jurisdiction would expect.

Args:
    identifier_type: one of "lei", "company_number", "name".
    identifier: the LEI, registration number, or legal name to look up.
    api_key: optional - a free key obtained from POST
        https://api.nkodatalabs.com/v0/keys. Without one, this call
        still works within a free anonymous trial (5 calls/day per
        caller IP) - see the response's "trial" field.
    jurisdiction: optional ISO-3166 alpha-2 country code (e.g. "GB", "ES", "FR").

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
api_keyNo
identifierYes
jurisdictionNo
identifier_typeYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed4 schema fields changed
    • addedInput schema / properties / api_key / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / api_key / default
      Added value: +null
    • removedInput schema / properties / api_key / type
      Removed value: -"string"
    • changedInput schema / required
      Previous value: -[
-  "identifier_type",
-  "identifier",
-  "api_key"
-]New value: +[
+  "identifier_type",
+  "identifier"
+]
  2. First observed

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does disclose rate-limit behavior (5 calls/day trial), that an api_key can be obtained via POST, and a response field ('trial'). However, it does not state side effects (though 'query' implies read-only), error/edge-case behavior, or response format beyond the trial field. It adds useful behavior but is not comprehensive.

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?

The description is economical: a one-sentence purpose followed by a clean Args list. No redundant content. The purpose sentence is slightly awkward and could be rephrased more directly, but every sentence earns its place.

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?

Input semantics are fully covered, and the purpose sentence implies the core result (whether a high-confidence match exists). However, with no output schema, the description does not describe the response shape or how to interpret match results beyond the trial field, leaving some ambiguity for an agent.

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

Parameters5/5

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

Schema description coverage is 0%, so the Args list is the only documentation. It clearly explains all four parameters: identifier_type with allowed values, identifier with definition, api_key with acquisition and trial behavior, and jurisdiction with ISO-3166 format and examples. This fully compensates for the schema's lack of descriptions.

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?

The description states a specific action – query whether an entity has a high-confidence registry match – identifying the resource (national commercial registry) and a unique purpose. The phrasing 'real LEI' and 'its declared jurisdiction would expect' is slightly convoluted, but the intent is clear; there are no siblings to differentiate from.

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 description establishes a clear context for use (checking registry match completeness) and provides operational guidance about the optional api_key and trial limits, but it never explicitly says when to prefer this tool over alternatives. With no sibling tools, a moderate score is appropriate.

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

All find-missing toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

award_state and find_missing are functionally distinct: one takes a TED award notice and resolves the winner's current registry status, while the other takes an LEI/company identifier and checks for a registry match. However, both revolve around commercial-registry existence/status, and the name 'award_state' could be misread as tender status rather than company status.

Naming Consistency2/5

Both names use snake_case, but there is no consistent grammatical pattern: 'award_state' is a noun-noun phrase while 'find_missing' is a verb phrase. The names also do not clearly signal their actual operations, making the convention feel disjointed.

Tool Count3/5

Two tools is borderline for a server, but it is defensible for a very narrow due-diligence/registry-check purpose. The set is not padded, but it feels thin compared to the breadth of registry and procurement scenarios it touches.

Completeness3/5

The two tools cover complementary registry checks, but there are notable gaps: there is no way to query a company's current status directly by identifier, no notice-discovery operations, and explicit coverage gaps for UK and Hungary. Core workflows are possible, but some users will hit dead ends.

Resources