Skip to main content
Glama

Sök och läs företagsärenden

arn_search_company_and_read

Sök endast i lokalt lagrade ARN-referat som uttryckligen godkänts mot exakt innehållshash och aktuell godkännandepost. Väntande, återkallade, ogiltiga eller saknade poster exponeras inte. Ingen livehämtning från ARN och ingen PDF-fallback. Täckningen är det godkända biblioteket, inte hela ARN:s databas. Saknade uppgifter fylls inte i. Anropet kan förbruka en fri användning, även vid upprepning.

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": {
      "company": "<company>"
    },
    "name": "arn_search_company_and_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
companyYes
outcomeNoobegransad
to_yearNo
categoryNoalla
from_yearNo
max_resultsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior5/5

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

Beyond the annotations it discloses the exact inclusion rule (approved hash plus current approval record), what is withheld (pending, revoked, invalid, missing records), the absence of live fetch and PDF fallback, the coverage boundary, and a non-obvious cost behavior: a call may consume one free usage even when repeated. That cost/idempotency detail is exactly the kind of context annotations cannot convey. There is mild tension with openWorldHint=true given the 'no live fetching' statement, but the annotation is broad enough that this reads as scope clarification rather than a contradiction.

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 exclusion set is front-loaded and each sentence carries operational information, with no filler or marketing language. There is some redundancy between 'Väntande, återkallade, ogiltiga eller saknade poster exponeras inte' and 'Saknade uppgifter fylls inte i', which restates the same absence guarantee. Slightly denser than necessary but well structured.

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?

Behaviorally the description is thorough for a six-parameter search tool with no output schema, covering corpus scope, exclusions, and cost. However, with 0% schema coverage and no output schema, an agent still lacks any guidance on how to set outcome, category, or year bounds, or what a result looks like. Complete on the 'what it will not do' axis, incomplete on the 'how to call it' axis.

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

Parameters2/5

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

Schema description coverage is 0% across six parameters, so the description carries the full burden and does not meet it: company, outcome, category, from_year, to_year, and max_results are never mentioned. It says nothing about accepted values (e.g. what 'obegransad' or 'alla' mean), date formats, or how max_results interacts with the approved-library cap. Only the general coverage limit hints indirectly at filtering behavior.

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 concrete action and a precise scope: search only in locally stored ARN case reports that were explicitly approved against an exact content hash and current approval record. It clearly rules out live ARN retrieval and PDF fallback, which separates it from tools that presumably fetch fresh data. It never explicitly names or contrasts with siblings such as arn_search_company or arn_search_and_read, and the 'read' half of the name is not described at all.

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?

It gives usable when-not guidance: no live fetching, no PDF fallback, coverage limited to the approved library, and missing data is never filled in, so an agent knows not to rely on it for complete or current ARN data. What is missing is a positive routing statement naming the alternative to use when live or full-database coverage is needed. The implicit guidance is strong but requires inference.

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.