Skip to main content
Glama

Нишка – отворен слой

Писмо до институция

prepare_letter
Read-onlyIdempotent

For a problem a person describes (in Bulgarian works best): which institution to write to, with its checked contact and the page it was checked on; the kind of letter (a signal about a problem in public space, a request for public information under ЗДОИ, or a complaint to a water or power company); the legal deadline for an answer and the date it falls on if you give the sending date; what the letter must contain; what to do if there is no answer; and, a ready Bulgarian draft with placeholders for the person's details for signals with a checked addressee. Never sends anything: a person reads, completes, signs and sends it. Also returns how often that institution answers, when Nishka has at least 5 reported outcomes.

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": {
      "problem": "<problem>"
    },
    "name": "prepare_letter"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoplovdiv (default), sofia, varna or burgas.
placeNoStreet, address or quarter, if not in the problem text.
sentOnNoYYYY-MM-DD the letter is (or was) sent, to compute the answer-by date.
problemYesThe problem in the person's words, e.g. „Дупка на тротоара пред бл. 14 в Тракия“.

Output Schema

NameRequiredDescriptionDefault
kindYes
noteNo
draftNo
categoryNo
addresseeYes
citationsYesEvery source the result rests on. Cite url; give checkedOn or publishedOn.
humanStepYes
escalationNo
alternativesNo
answerDeadlineNo
responsivenessNo
requiredContentNo

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

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral context: 'Never sends anything: a person reads, completes, signs and sends it', which fixes the human-in-the-loop boundary. It also discloses a conditional behavior beyond the annotations — responsiveness data is returned only 'when Nishka has at least 5 reported outcomes' — and the placeholder-based draft format. Nothing here contradicts the annotations.

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 and scope are front-loaded and no clause is filler — every semicolon-separated item is a distinct output. However, it is delivered as one long run-on sentence of roughly 120 words, which makes it harder to scan than a short bulleted enumeration would be.

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?

An output schema exists, so return shape need not be described, yet the description helpfully summarizes the deliverable's parts and its one conditional (minimum 5 outcomes for responsiveness). Combined with full annotation coverage of the safety profile, an agent has what it needs to call this correctly; only minor gaps remain, such as supported geography being left to the schema.

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 the baseline is 3; each parameter is already documented including the city enum and default. The description adds only light meaning, notably that Bulgarian input 'works best' and that the answer-by date is computed only 'if you give the sending date', which largely restates the schema's own wording for sentOn.

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 (prepare a letter) and then enumerates the concrete outputs: target institution with checked contact and source page, letter type (signal, ЗДОИ request, utility complaint), legal deadline and answer-by date, required contents, escalation if unanswered, and a ready Bulgarian draft with placeholders. This is far more specific than the title alone and is clearly distinguishable from siblings like institution_responsiveness or srok_deadline, which return single facts rather than a composed deliverable.

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?

Opening clause sets the trigger clearly: 'For a problem a person describes (in Bulgarian works best)'. It also implies the input contract (a described problem, optionally a sending date to compute the answer-by date). No explicit when-not or named alternative is given, but no sibling performs this composite task, so the gap is minor.

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