Skip to main content
Glama

Нишка – отворен слой

Срокове за документи и плащания

document_deadline
Read-onlyIdempotent

When a Bulgarian identity card, passport or driving license expires, when a car's technical inspection is due, the vignette periods, and the local tax dates (moved to the next working day when they fall on a non-working day) — each rule with its official source. Works the date out only where the rule is unambiguous (e.g. an ID card issued at 18–70 is valid 10 years); otherwise says so and the person reads the date on the document.

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": {
      "kind": "<kind>"
    },
    "name": "document_deadline"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
yearNoFor local taxes: the year (default this year).
categoryNoDriving license category, e.g. B or C1E.
issuedOnNoYYYY-MM-DD the document was issued (for an inspection: the latest passed one).
birthDateNoYYYY-MM-DD, for ID cards and passports (validity depends on age at issue).
firstRegistrationNoYYYY-MM-DD the car was first registered as new.

Output Schema

NameRequiredDescriptionDefault
kindYes
ruleYes
expiryNo
taxDatesNo
citationsYesEvery source the result rests on. Cite url; give checkedOn or publishedOn.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / citations / items / properties / licence / enum
      Previous value: -[
      -  "CC-BY-4.0",
      -  "official-record"
      -]New value: +[
      +  "CC-BY-4.0",
      +  "official-record",
      +  "ODbL-1.0"
      +]
  2. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: results are tied to an official source, local tax dates shift to the next working day, and the tool deliberately refuses to compute when the rule is ambiguous. That refusal semantics is the most valuable disclosure for an agent deciding how much to trust output.

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?

Dense but efficient — two sentences with no filler — and the enumeration of covered document types is front-loaded. It opens with a subordinate clause rather than a main statement, which makes the first read slightly awkward, but nothing is redundant or padded.

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?

With six parameters, an enum-gated 'kind', and an output schema already documenting return values, the description covers what it must: scope, the working-day rule, and the ambiguity fallback. The remaining gap is modest — it does not indicate that different kinds consume different parameter subsets, so an agent must consult the schema to know which optional fields matter.

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 already 83%, so the schema carries most parameter meaning; the baseline of 3 applies. The description does reinforce the age-at-issue dependency behind birthDate ('an ID card issued at 18–70 is valid 10 years'), but it never explains which parameters pair with which kind, nor the role of firstRegistration, category, or year in the computation.

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 names the concrete subject matter (ID card, passport, driving licence expiry, technical inspection, vignette, local tax dates) and states that each rule comes with its official source, plus that dates are computed only where the rule is unambiguous. That is a clear picture of the tool's function, though it is delivered as a topic list rather than a direct verb+resource statement and never distinguishes it from siblings like srok_deadline or srok_day.

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?

Usage is implied rather than stated: an agent can infer it should call this when it needs a Bulgarian document or tax deadline. The one genuine piece of guidance is the fallback condition — if the rule is ambiguous the tool says so and the person reads the date off the document — which is a 'when-not' of sorts. No comparison to alternatives or prerequisites is given.

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.

Resources