Skip to main content
Glama

datovka_send_draft

Destructive

Sends a locally approved, immutable draft from a Czech data box in one attempt. On failure, verify sent messages before creating or retrying any draft manually.

Instructions

Odesle pouze lokalne schvaleny nemenny navrh, nejvyse jeden pokus.

Po chybe nejprve overte odeslane zpravy. Nevytvarejte automaticky novy navrh pro opakovani. Schvaleni nema MCP nastroj.

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": {
      "draft_id": "<draft_id>"
    },
    "name": "datovka_send_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
draft_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already flag destructive=true, idempotent=false and openWorld=true; the description adds the operationally decisive facts beyond them — a hard cap of one attempt, a defined error-recovery procedure, and an explicit prohibition on automatic re-creation of the draft. For a non-idempotent destructive send this is exactly the behavioral context an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each carrying a distinct rule: scope, error handling, and the out-of-band approval caveat. The hard constraint ('one attempt') is front-loaded and nothing is 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?

For a destructive, non-idempotent operation with no output schema, the description covers the safety-relevant behavior and error path well. The remaining gap is minor: it never says where draft_id originates or whether the draft persists after sending.

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?

There is a single required parameter (draft_id) with 0% schema description coverage, and the description does not explain its format or that it comes from the draft-listing/read siblings. The parameter name is largely self-explanatory, which keeps this at minimum-viable rather than deficient.

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 verb+resource are concrete ('Odesle ... navrh' = send a draft) and the scope is narrowed by two real constraints: the draft must be locally approved and immutable, and only one attempt is allowed. It distinguishes itself implicitly from the preparation/listing siblings through the 'locally approved' precondition, but it never names an alternative tool, so it falls just 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 Guidelines5/5

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

Explicit when-to-use is baked in (only an approved immutable draft) and the when-not is spelled out: do not auto-create a replacement draft to retry, and after an error verify sent messages first. It also states that approval happens outside MCP ('Schvaleni nema MCP nastroj'), closing the obvious 'where do I approve?' loop.

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