Skip to main content
Glama

Applystead

by com.applystead
OverviewDiscussionsAdmin

Connected apps and keys

manage_connections
Destructive

Disconnect a connected app, revoke an API key or remove a webhook. Keys and webhooks are created in Agents & API. Actions: disconnect_agent, revoke_key, remove_webhook. Call with action "help" for each action's fields.

Input Schema

NameRequiredDescriptionDefault
actionYes
key_idNoAn API key's id from get_connections list.
paramsNoFields for the action. Call with action "help" to list each action's fields.
grant_idNoA connected app's id from get_connections list.
webhook_idNoA webhook's id from get_connections list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "list",
-  "disconnect_agent",
-  "revoke_key",
-  "remove_webhook",
-  "help"
-]New value: +[
+  "disconnect_agent",
+  "revoke_key",
+  "remove_webhook",
+  "help"
+]
    • changedInput schema / properties / grant_id / description
      Previous value: -"A connected app's id from manage_connections list."New value: +"A connected app's id from get_connections list."
    • changedInput schema / properties / key_id / description
      Previous value: -"An API key's id from manage_connections list."New value: +"An API key's id from get_connections list."
    • changedInput schema / properties / webhook_id / description
      Previous value: -"A webhook's id from manage_connections list."New value: +"A webhook's id from get_connections list."
  2. Added

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the destructive nature is covered structurally. The description adds which concrete resources get destroyed and where keys/webhooks originate (Agents & API), but says nothing about reversibility, confirmation, or auth requirements.

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 short sentences, front-loaded with the core destructive actions before enumerating the action names and the help affordance. Slight redundancy between listing the actions and pointing at help, but nothing is wasted.

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 multiplexed action-dispatch tool with a free-form nested params object and no output schema, the description covers the available actions and routes the agent to the "help" action for per-action fields, closing the main gap. It could say more about which id pairs with which action, but the schema covers that.

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 coverage is 80% and the eight-hex/32-hex id formats plus their provenance are documented in the schema itself. The description restates the action enum values already present in the schema, adding only the "help" discovery hint, which the params field description also carries. Baseline 3 is appropriate.

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 specific verbs and their resources (disconnect a connected app, revoke an API key, remove a webhook), so the agent immediately knows this is the write/destroy counterpart to get_connections. It does not explicitly name get_connections as the read sibling, leaving that differentiation implied rather than stated.

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

Usage Guidelines3/5

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

Usage is implied through the enumerated actions and the pointer to action "help" for per-action fields, which is genuinely useful routing. However, there is no explicit guidance on when to use this versus get_connections, nor prerequisites (e.g., obtaining the id first).

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

All Applystead toolsInspect
Try in Browser
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources