Skip to main content
Glama

datovka_prepare_message

Prepares an immutable local draft for a Czech data box message without sending it; review and approve separately before dispatch.

Instructions

Ulozi nemenny navrh lokalne; nic neodesila. files je JSON pole priloh.

Zobrazte uplny nahled. Schvaleni pouze v mistnim okne prikazem datovka-config review ID. Nevydavejte pripravu za odeslani.

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": {
      "from_box_alias": "<from_box_alias>",
      "to_box_id": "<to_box_id>",
      "subject": "<subject>"
    },
    "name": "datovka_prepare_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNo
filesNo[]
subjectYes
to_box_idYes
from_box_aliasYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only say it is a non-destructive, non-open-world write; the description adds key behavior beyond that: the draft is immutable, nothing is transmitted, and approval happens through an external local window/review command. It does not describe what happens on name collisions or what the tool returns, so it is strong but not exhaustive.

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-loads the crucial local-only, send-nothing constraint, then adds the attachment note and the approval procedure. It is compact with no filler, though the mix of behavior description and imperative instructions is slightly disjointed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter, no-output-schema write tool, the description covers the safety/approval model well but leaves the meaning of four required/optional parameters unexplained. It also does not state return behavior or whether the draft persists across sessions, which matters for an immutable local draft.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 5 parameters, and the description only clarifies one of them ('files je JSON pole priloh'). from_box_alias, to_box_id, subject, and body receive no added meaning, so the description leaves most parameter semantics undocumented.

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 concrete verb+resource: it saves an immutable draft locally and explicitly sends nothing ('Ulozi nemenny navrh lokalne; nic neodesila'). It also distinguishes itself from the sending path by warning 'Nevydavejte pripravu za odeslani', which separates it from datovka_send_draft.

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?

Gives clear operational guidance: show the full preview ('Zobrazte uplny nahled') and obtain approval only via the local command datovka-config review ID. It does not name a specific alternative tool by name, but the when/when-not framing against sending is explicit.

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