Skip to main content
Glama

dashy_config

Destructive

List or retrieve Dashy configuration files as JSON, or replace a file with confirm-gated writes that default to a dry-run preview.

Instructions

List config files, get one file as JSON, or replace a whole file. Replace runs only when confirm is true and DASHY_ALLOW_WRITES=true. Otherwise it is a dry-run and no HTTP write is sent. List accepts offset and limit applied after the fetch. Actions: list, get, replace.

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": {
      "action": "<action>"
    },
    "name": "dashy_config"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoClient-side page size. Applied after the full list is fetched.
actionYesDashy operation to call.
offsetNoClient-side start index. Dashy has no page query. Omitted returns the full list.
confirmNoBoolean true runs the write when DASHY_ALLOW_WRITES is true. Omit it or pass false for a dry-run preview that sends nothing. The string true is rejected.
documentNoJSON object body. Section adds need name. Item adds need title.
filenameNoConfig basename in the user-data directory, for example conf.yml.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

The annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds genuinely useful context beyond them: the env-var gate and the dry-run fallback that sends no HTTP write. That is a real behavioral disclosure the annotations cannot convey. It stops short of describing the response shape or what happens when a file is missing, leaving some gaps for a destructive tool.

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?

Sentences are dense and front-loaded, with the destructive gate stated early. The trailing 'Actions: list, get, replace' merely restates the opening sentence and earns little, and the offset/limit sentence duplicates the schema, so it is not waste-free.

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 six-parameter tool with a destructive branch and no output schema, the description covers the essentials: what each action does, the write-gating condition, the dry-run behavior, and the client-side pagination model. What is missing is minor, such as error behavior on a nonexistent filename or whether replace requires a full document.

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

Parameters4/5

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

With 100% schema coverage the baseline is 3, and the description adds a little meaning: it clarifies that offset and limit are applied after the fetch rather than as server-side paging. However, the schema already states this almost verbatim ('Applied after the full list is fetched'), so most of the description's parameter content is repetition rather than new 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?

The description names three concrete operations on config files (list, get, replace) with specific verbs and a clear resource, so an agent knows exactly what the tool covers. It does not explicitly distinguish itself from siblings like dashy_items or dashy_sections, but 'whole file' replace versus the schema's section/item adds implicitly separates the scope.

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 precise when-it-runs rule for the destructive path: replace only executes with confirm true AND DASHY_ALLOW_WRITES=true, otherwise it is a dry-run that sends no HTTP write. That is strong conditional guidance, though it says nothing about choosing between list and get, or when to prefer a sibling tool.

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