SandiMorse

Decode a scout code

decode_scout_code

Read-onlyIdempotent

Reads a coded message back to text in angka, koordinat, Merah Putih, Polybius, AZ (Atbash), AN (ROT13), kimia, jam, AND, Napoleon or ular. Kotak, rumput and semaphore are drawings and have no text reader. Returns the decoded text, the key used and a link to the SandiMorse page with the same input.

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": {
      "code": "<code>",
      "text": "<text>"
    },
    "name": "decode_scout_code"
  }
}

Input Schema

Name	Required	Description
`code`	Yes	Code to read.
`hour`	No	Hour of the letter A in jam, 0 to 23. Default 8.
`step`	No	Step between letters: a number for angka (default 1) or minutes for jam (default 5).
`text`	Yes	The coded message, for example numbers for angka, letter pairs for koordinat, times for jam or a formula for kimia.
`start`	No	Number for the letter A in angka. Default 1.
`width`	No	Letters per row in napoleon (default 6) or ular (default 4), 2 to 30.
`minute`	No	Minute of the letter A in jam, 0 to 59. Default 0.
`reading`	No	Reading order of ular: snake reads rows back and forth, column reads top to bottom. Default snake.
`language`	No	Language of the answer and of the page the link opens: id for Indonesian or en for English. Default id.
`top_word`	No	Column key word of koordinat: 5 different letters A to Z. Both key words are needed for a custom key.
`left_word`	No	Row key word of koordinat: 5 different letters A to Z.

Output Schema

Name	Required	Description	Default
`item`	Yes
`view`	Yes
`language`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.2/5.0

Behavior4/5

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

The annotations already declare readOnly, idempotent and non-destructive behavior, and the description adds the useful constraint that drawing-based codes cannot be read at all. It also previews the return payload (decoded text, key used, SandiMorse link), though that overlaps with the existing output schema.

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?

Three sentences, front-loaded with the capability, then the exclusion, then the return value. The long enumeration of code names is long but necessary because it defines the supported enum space for the agent.

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

Completeness5/5

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

With an output schema covering return values and full schema parameter documentation, the description only needs to establish scope and the drawing-code exclusion, which it does. Nothing required to call the tool correctly is missing.

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%, and every parameter including hour, step, width and the koordinat key words is documented in the schema itself. The description adds no format hints or constraints beyond that, so the baseline of 3 applies.

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?

The description opens with a specific verb and resource ('Reads a coded message back to text') and enumerates every supported code type, which cleanly separates it from the sibling encode_scout_code. An agent can determine direction (decode, not encode) without opening the schema.

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?

It gives a concrete negative case — 'Kotak, rumput and semaphore are drawings and have no text reader' — steering the agent away from unsupported inputs. It stops short of naming encode_scout_code as the counterpart for the reverse operation, so routing is implied rather than explicit.

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

All SandiMorse tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.