Skip to main content
Glama
Sign In

Lilambd Data for Agents

by io.github.Veniwol-Li-Lambd
OverviewDiscussionsAdmin

rules-ahead

Which new rules on my topic are coming in Japan or the US, and when can I still comment?. One finished brief per topic: Japanese e-Gov public-comment drafts still open, US Federal Register proposed rules with open comment windows, US final rules and Japanese law amendments published but not yet in force, and recent Japanese comment results with the number of comments received. Plain English or Japanese keywords (drone, AI, food labeling, tax, 建築, 医薬品). Deadlines, days left, counts and topic matching computed by Lilambd from official registers; every item links to its official page. Japanese titles stay in Japanese; US items carry title_en. Facts only, not legal advice. Routes: /answer (topic*, country, limit, routine); /topics (country, limit); /upcoming (country, status, topic, kind, stage, agency, category, since, until, sort, limit, offset). Paid $0.5 USDC per call via x402 (_meta["x402/payment"]); set sample=true for a free 3-row preview.

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": {
      "route": "<route>"
    },
    "name": "rules-ahead"
  }
}

Input Schema

NameRequiredDescriptionDefault
routeYesOne of: /answer, /topics, /upcoming. Replace {placeholders} with a value, e.g. /search or /HND.
paramsNoQuery parameters, e.g. {"q":"tokyo","limit":"50"}
sampleNoFree preview, max 3 rows

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses the paid model ($0.5 USDC per call via x402 _meta), the free 3-row sample mode, that deadlines/days-left/counts/topic-matching are computed by the provider rather than raw, and that every item links to its official page. It also flags a scope limit ('Facts only, not legal advice') and output conventions (Japanese titles kept in Japanese, US items carry title_en). It leaves out pagination limits, rate limits, and error behavior, which is why it is not a 5.

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 core question is front-loaded and every clause adds something: content categories, keyword guidance, computed-field provenance, output conventions, and access/pricing. It is dense and somewhat run-on, and the 'Facts only, not legal advice' line is a low-value disclaimer, but there is little outright padding.

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?

For a 3-parameter wrapper tool with no annotations and no output schema, the description covers what an agent needs: which routes exist, what each accepts, what kinds of records come back, what fields to expect, and how billing and the free preview work. Remaining gaps are response envelope shape and the enumerated values for filtering parameters, which matter when composing /upcoming queries.

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

Parameters4/5

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

The schema is only a generic route/params/sample wrapper with a catch-all string map, so the description is where the real parameter meaning comes from. It enumerates the accepted route values and, more importantly, the per-route query keys (/answer: topic*, country, limit, routine; /upcoming: country, status, topic, kind, stage, agency, category, since, until, sort, limit, offset), plus valid keyword style with examples. It does not give accepted values for status/kind/stage/sort or explain 'routine', so it is informative but incomplete.

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 opening question plus the enumeration of the four item categories (open Japanese e-Gov comment drafts, US proposed rules with open comment windows, US final and Japanese amended-but-not-in-force rules, recent Japanese comment results) makes the resource and scope unmistakable. It does not name any sibling tool to contrast with, so it falls short of a 5, but the regulatory-tracking domain is distinct enough from siblings like japan or pulse that confusion is unlikely.

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 states concrete conditions for use (Japan or US rules on a topic, with comment deadlines) and gives a route-selection map: /answer for topic-based answers, /topics for topic discovery, /upcoming for filtered browsing. It also explains the free-preview escape hatch (sample=true, 3 rows) versus the paid call. It stops short of explaining when to prefer /topics over /answer or what 'routine' selects, so guidance is clear but not exhaustive.

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

All Lilambd Data for Agents 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