Skip to main content
Glama
Sign In

Lovly

by no.lovlyai
OverviewDiscussionsAdmin

Spør Lovly

ask_lovly

Ask Lovly a question about Norwegian law. The answer is grounded in current Norwegian laws and central regulations from Lovdata and cites the sections it relies on, with lovdata.no links. Answers follow the question's language. Each call counts as one question on the user's Lovly account, exactly as on lovlyai.no: a subscription, an active 7-day pass or a purchased question pays for a full answer. Without one, the user gets 3 free previews a day (the opening of the answer plus its sources); if the user buys access, unlock_answer returns the full answer.

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": {
      "question": "<question>"
    },
    "name": "ask_lovly"
  }
}

Input Schema

NameRequiredDescriptionDefault
historyNoEarlier questions and Lovly answers in this conversation, oldest first, when the question is a follow-up. Lovly uses the last few.
languageNoISO 639-1 code of the language to answer in, such as "no" or "en". Detected from the question when left out.
questionYesThe question, at most 2000 characters. Include the facts that matter (who, what, when) so Lovly finds the right rules.
plain_languageNoExplain in plain language (klarspråk) for someone without legal training, like Lovly's Tolken.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing the metered cost (each call consumes one question), the degraded free-tier behavior (3 previews/day containing only the answer opening plus sources), and the language-following behavior. This is exactly the quota and truncation context an agent needs before calling a non-idempotent, non-read-only tool.

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?

Purpose is front-loaded in the first sentence, followed by output/grounding, then the cost model. Every sentence carries decision-relevant information with no filler or repetition of the title.

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?

With no output schema, the description still characterizes the return value (cited sections, lovdata.no links, preview truncation). Combined with the quota explanation and pointer to unlock_answer, an agent has everything needed to call and interpret the result.

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 schema already documents question length limits, history ordering, language codes, and plain_language. The description only reinforces the language behavior implicitly; it adds no extra semantics for history or plain_language, so the baseline of 3 applies.

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?

States a specific verb and resource ("Ask Lovly a question about Norwegian law") plus the grounding source (Lovdata laws and central regulations) and output form (cited sections with lovdata.no links). It also differentiates itself from the sibling by naming unlock_answer as the follow-up that returns the full answer.

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?

Explains the access conditions under which this tool is the right call (subscription, 7-day pass, purchased question) and points to unlock_answer when the user buys access after a preview. It does not give explicit when-not guidance or direct the agent to get_lovly_account for entitlement checks before calling.

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

All Lovly toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources