Skip to main content
Glama

Data Breach Notification Deadlines

by io.github.Nero-Engine
OverviewDiscussionsAdmin

who_to_notify

Works out every data breach notice a company owes and the deadline for each. Give affected (how many people in each US state or country), the data types exposed (for example ssn, drivers_license, payment_card, financial_account, medical, health_insurance, username_password, biometric, passport, dob, email_address), whether the data was encrypted with the key kept safe, the date the breach was discovered, and flags: sec_registrant (US public company), sector (hipaa_covered_entity, hipaa_business_associate, glba_financial, health_app, nydfs_licensee) and role (owner, or service_provider holding data for another company). Returns each notice owed (people affected, state attorneys general, credit bureaus, HHS, SEC Form 8-K, FTC, EU and UK data protection authorities, Canada, Australia) with the deadline as a date where the law sets a fixed period, the deadline rule in words, what the notice must contain, how to send it and the official source, earliest first. Unclear cases give the SAFE answer (notice treated as required) plus what it depends on. Free.

Input Schema

NameRequiredDescriptionDefault
roleNoowner (default): the company that owns or licenses the data. service_provider: holds it for another company, which mostly means notifying that company quickly.
sectorNoSector rules that apply: hipaa_covered_entity, hipaa_business_associate, glba_financial (non-bank financial firms under the FTC Safeguards Rule), health_app (FTC Health Breach Notification Rule), nydfs_licensee (New York DFS regulated).
affectedYesWhere the affected people live: [{"state":"CA","count":1200},{"state":"TX","count":300},{"country":"Germany","count":40},{"country":"United Kingdom","count":15},{"country":"Canada","province":"Quebec","count":5}]. A bare two-letter code is read as a US state (CA = California); use {"country":"CA"} or "Canada" for Canada.
encryptedNoTrue only if all the exposed data was encrypted and the key was not exposed. Many US state laws then need no notice. Default false.
data_typesNoPersonal data exposed, for example ["ssn","drivers_license","payment_card"]. If left out every law is treated as triggered (SAFE).
sec_registrantNoTrue for a company that files reports with the US SEC (listed in the US). Adds Form 8-K Item 1.05.
date_discoveredNoDate the breach was discovered (or you became aware of it), YYYY-MM-DD. Defaults to today. Deadlines are counted from it.
materiality_dateNoSEC registrants: date the company decided the incident is material, YYYY-MM-DD. The 8-K is due 4 business days after it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does well: it discloses defaults ('encrypted' false, discovery date defaults to today, omitting data_types treats all laws as triggered), the failure mode for ambiguity ('Unclear cases give the SAFE answer ... plus what it depends on'), result ordering (earliest first), and cost/auth ('Free'). This is substantive behavioral context beyond the 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?

Front-loaded with the purpose, then the required inputs, then the return shape and the safe-answer rule — a logical order with no filler sentences. It runs long and duplicates several parameter lists already in the schema, which is the only waste.

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 8 parameters, no output schema and no annotations, the description must explain returns and does: each notice owed, the deadline date or rule-in-words, required contents, delivery method, and official source, plus ordering. Nothing essential for correct invocation is missing.

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 every parameter is already documented in the schema; the description largely restates those same semantics (affected shapes, data_types examples, encrypted, date_discovered, sector/role flags). It adds little parameter meaning the schema does not already supply, so the 3 baseline 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 computation and its output: 'Works out every data breach notice a company owes and the deadline for each,' then enumerates the notice classes (state AGs, credit bureaus, HHS, SEC 8-K, FTC, EU/UK DPAs, Canada, Australia). This is unmistakably a computation-over-inputs tool, clearly distinct from a jurisdiction lookup like list_breach_laws.

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

Usage Guidelines3/5

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

The description implies the usage context by listing the facts to supply (affected counts, data types, encryption, discovery date, registrant/sector/role flags), but never states when to reach for this tool rather than list_breach_laws, nor any when-not condition. Usage is inferable but not spelled out.

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

All Data Breach Notification Deadlines 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