Skip to main content
Glama

Нишка – отворен слой

Търсене в Извор

search_izvor
Read-onlyIdempotent

Search Извор, an index of Bulgarian primary official sources (e.g. the State Gazette, municipal council decisions, public procurement notices). Returns the official record's title, issuer, number, date and official URL. Cite the official URL, not Извор; the excerpt is for orientation only.

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": {
      "query": "<query>"
    },
    "name": "search_izvor"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoLatest publication date, YYYY-MM-DD.
fromNoEarliest publication date, YYYY-MM-DD.
limitNo
queryYesWords to find, in Bulgarian, e.g. „бюджет 2027“, „решение ремонт улица“.
sourceNoLimit to one source id (see about_izvor).

Output Schema

NameRequiredDescriptionDefault
citationsYesEvery source the result rests on. Cite url; give checkedOn or publishedOn.
documentsYes

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. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the description is not needed for the safety profile. It nonetheless adds real context beyond them: the result fields returned (title, issuer, number, date, official URL) and the important caveat that the excerpt is orientation only and the official URL must be cited. It does not discuss result caps or pagination behavior beyond the schema's limit.

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?

Two tight sentences, front-loaded with the corpus definition and followed by return fields and citation guidance; nothing is padded. Minor friction: it refers to 'the excerpt' as an output even though the enumerated return fields omit it, a small inconsistency in an otherwise clean structure.

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 an output schema present and 80% parameter coverage, the description only needs to orient the agent, and it does so by naming the corpus, the return fields and the citation rule. The main remaining gap is routing against sibling search tools, which matters given the size of the sibling list.

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 80%, so the schema already documents query, from/to, limit and source, including the Bulgarian-language hint for query. The description adds no parameter-level meaning such as how date filters interact with query or what a source id looks like. Baseline 3 is appropriate when the schema carries the semantics.

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?

States a specific verb (Search) plus the resource and even characterizes the corpus with concrete examples (State Gazette, municipal council decisions, procurement notices). That is far clearer than a bare name restatement. It does not differentiate itself from the sibling search_osnova, which is also a search tool, so it stops short of a 5.

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 only implied: an agent can infer this is the entry point for finding official Bulgarian records. The one explicit directive — 'Cite the official URL, not Извор' — governs how to use results, not when to pick this tool over search_osnova or get_izvor_document. No when-not or alternative routing 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