Skip to main content
Glama

Kreditvurdering

kreditvurdering
Read-onlyIdempotent

Kreditvurdering med score 1-100 (højere er bedre), kategori (lav/middel/høj risiko), forklarlige faresignaler med kilde og de vigtigste faktorer. Vurderes både for selskabet alene og med koncernen (en solid moder kan løfte et svagt datterselskab). Svaret har også seneste egenkapital og årets resultat (seneste_regnskab, med periode), så du ikke behøver hent_regnskab til det; kald hent_regnskab i samme omgang uden at spørge, hvis brugeren vil se omsætning eller flere år. Brug det til "er X en sikker kunde?". Eksempel: {"cvr": "10150817"}. Faresignalerne tæller også meddelelser i Statstidende (konkursdekret m.m., feltet statstidende har dem med link). Scoren er en vurdering ud fra offentlige data, ikke rådgivning; sig det til brugeren. Kræver betalt pakke (gratis nøgle: smagsprøver). Tæller 1 opslag.

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": {
      "cvr": "<cvr>"
    },
    "name": "kreditvurdering"
  }
}

Input Schema

NameRequiredDescriptionDefault
cvrYesCVR-nummer med 8 cifre, fx "10150817". Kender du kun navnet, så brug soeg_virksomhed først.
detaljerNo"kort" (standard) giver de vigtigste felter. "fuld" giver alle felter.kort

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, but the description adds material context they cannot carry: it requires a paid package (free key via 'smagsprøver'), consumes 1 lookup, warns that the score is an assessment from public data and not advice that must be disclosed to the user, and notes Statstidende notices (bankruptcy decrees) feed the warning signals. It also explains the dual standalone-vs-group scoring logic, which is non-obvious behavior.

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 opening sentence front-loads the return payload and the following sentences each add distinct value (sibling routing, cost, disclaimer). It is dense but slightly overpacked: the inline JSON example duplicates the schema example, and the licensing/disclaimer notes are interleaved mid-paragraph rather than grouped.

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?

There is no output schema, so the description carries the full burden of explaining return values, and it does so thoroughly (score, category, warning signals with source, main factors, seneste_regnskab with period). Combined with the cost/licensing disclosure and the sibling-routing rule, an agent has everything needed to call it correctly and report results responsibly.

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% and both parameters are fully documented in the schema itself, so the baseline is 3. The description only repeats the CVR example and the soeg_virksomhed prerequisite already present in the schema, and it never explains what the 'detaljer' enum ('kort' vs 'fuld') changes in the response.

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 states a concrete verb+resource (credit assessment of a company by CVR) and enumerates the exact payload: score 1-100, risk category, explainable warning signals with source, and key factors. It further distinguishes the output from sibling hent_regnskab by noting equity and profit are included, so an agent can tell the two apart without opening a schema.

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

Usage Guidelines5/5

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

It gives an explicit trigger ('Brug det til "er X en sikker kunde?"'), an explicit exclusion (you do not need hent_regnskab for equity/profit), and an explicit follow-up rule (call hent_regnskab in the same turn without asking if the user wants revenue or multiple years). A prerequisite is also named: if you only know the name, use soeg_virksomhed first.

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