Skip to main content
Glama

PeppolStatus

by com.peppolstatus
OverviewDiscussionsAdmin

get_deregistered_stats

Read-only

Get the De-registered overview

The participants that left the network. A De-registered ID is a participant that is not registered now AND has at least one closed registration row. An ID that was never observed registered (not scanned yet, or never in the SML) is not de-registered: it is counted apart in never_registered and is in no other number here. leavers is the sub-count of the De-registered IDs that left while a Provider served them.

deregistered, share_pct and countries are the stock of the daily rollup (as_of). flow and weekly are the leave flow from the network growth series of /v1/network/stats, to the last complete UTC day: flow.d7 and flow.d30 are the same counts as leavers.last_7d and leavers.last_30d there. A day with no completed change scan is a gap: its de-registrations are counted on the next scanned day, so a period sums all its days and gap_days only marks it. A period or a week of gap days only has leavers: null — a gap is never 0. Joiners do not depend on the change scan, so a gap day keeps them. annualized_leave_rate_pct is the Leaver rate (annualized), the same figure as leavers.annualized_pct of /v1/network/stats: the 30-day leavers as a percentage of the registered participants at the start of the period, × 365 / the days of the period. Leave dates are reliable from 2026-08-02 (reliable_from); a period that would open earlier is clamped to it, and the weekly trend starts there. The event date of a de-registration is about 3 days after the true leave (3 consecutive scans without the ID).

Free. The company breakdown of the same population is /v1/stats/deregistered/companies (Market).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

With only `readOnlyHint: true` annotated, the description adds extensive behavioral context: gap-day handling, `leavers: null` semantics, `reliable_from` clamping, and the roughly 3-day lag between true leave and event date. These details materially affect how an agent interprets the returned stats and are not available from annotations or schema.

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 purpose is front-loaded and the dense metric explanations are relevant because there is no output schema to carry them. The block is long and could be better structured with headings or bullets, but nearly every sentence contributes to correct interpretation.

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?

Given the lack of an output schema, the description thoroughly defines the returned fields (`deregistered`, `share_pct`, `countries`, `flow`, `weekly`, `leavers`, `gap_days`, `annualized_leave_rate_pct`) and their caveats. It provides enough context for an agent to understand and use the stats correctly.

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 tool takes zero parameters, so there are no parameter semantics to document. Per the rubric, a zero-parameter tool has a baseline of 4.

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 ('Get') and resource ('De-registered overview'), then immediately defines the de-registered population and contrasts it with never_registered. It also distinguishes related endpoints, including the company breakdown at `/v1/stats/deregistered/companies` and the flow source at `/v1/network/stats`, so an agent can tell it apart from siblings.

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?

Provides clear context for when this overview is the right population to inspect and names the sibling endpoint for company breakdown. It does not explicitly state when not to use it or how it relates to `list_deregistered_ids`, but the alternatives are visible enough for selection.

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

All PeppolStatus 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