Skip to main content
Glama

Remove a source

remove_source
Destructive

Disconnects a connected data source and deletes its stored keychain password; when used from web clients, returns the local command to run.

Instructions

Remove a connected source, and its password from the keychain. From claude.ai or ChatGPT on the web it only gives the command the user runs on their computer.

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": {
      "name": "<name>"
    },
    "name": "remove_source"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, but the description adds two non-obvious behaviors beyond them: the keychain password is deleted alongside the source, and when invoked from claude.ai or ChatGPT on the web it returns a shell command instead of performing the removal. It does not mention reversibility or any confirmation step, which would complete the picture 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?

Two short sentences, front-loaded with the destructive action, with no filler. The second sentence is slightly compressed in phrasing but every clause carries information about scope or behavior.

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 destructive, single-parameter tool with no output schema, the description covers the blast radius (source plus keychain password) and one important environment caveat. It leaves the meaning of "name" and the return value/shape of the web-mode command unexplained, which an agent needs to call it correctly.

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 coverage is 0% for the single "name" parameter, so the description carries the full burden and does not meet it: it never says whether name is the source label from list_sources, an ID, or a hostname, and gives no format or example. "Connected source" only weakly hints at the value expected.

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?

States a specific verb and resource ("Remove a connected source") plus an adjacent effect ("its password from the keychain"), which clearly separates it from add_source and list_sources. It stops short of naming a sibling explicitly, so it is clear but not fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

There is no explicit statement of when to use this instead of add_source, describe_source, or list_sources, and no preconditions such as confirmation or required login state. The web-mode sentence describes what happens rather than guiding tool selection, so usage is only implied by the verb.

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