Skip to main content
Glama
Sign In

AccountHub

by ai.accounthub
OverviewDiscussionsAdmin

update_shared_item

Destructive

Edit the title, body or due date of an item you placed in an AccountHub shared project (shared project) — NOT a Slack workspace — or, with mark_decided: true, turn an open question into a decision. Only the person who placed an item can edit its text, and only while still a member. A chat message — a note or a plain message in an AccountHub chat — follows the chat rule: its text (title / body; body, if given, is the whole new text) can be fixed only within 15 minutes of placing it and then shows as edited, the same as edit_chat_message; its due date stays editable any time. Decisions, open questions and to-dos have no time limit. mark_decided follows who may close the question (its placer, anyone while unassigned, or its assignee). To change who does it use reassign_shared_item, to change its state use complete_shared_item.

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": {
      "item_id": "<item_id>"
    },
    "name": "update_shared_item"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoNew body; null clears it.
titleNoNew title.
item_idYesThe item id (from list_shared_items).
due_dateNoNew deadline YYYY-MM-DD; null clears it.
mark_decidedNotrue = turn an open question into a decision (who decided it and when is recorded). Send it alone, without title/body/due_date. Allowed for whoever may close the question: its placer, anyone while it is unassigned, or its assignee.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • removedInput schema / properties / body / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • addedInput schema / properties / body / type
      Added value: +[
+  "string",
+  "null"
+]
    • removedInput schema / properties / due_date / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • addedInput schema / properties / due_date / type
      Added value: +[
+  "string",
+  "null"
+]
  2. Changed1 schema field changed
    • addedInput schema / properties / mark_decided
      Added value: +{
+  "description": "true = turn an open question into a decision (who decided it and when is recorded). Send it alone, without title/body/due_date. Allowed for whoever may close the question: its placer, anyone while it is unassigned, or its assignee.",
+  "type": "boolean"
+}
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare destructiveHint=true and a title, so the description carries most of the burden and does so well: it discloses the 15-minute edit window for chat message text, the visible 'edited' marker, that due dates stay editable indefinitely, and that body when supplied is the entire replacement text (destructive overwrite). It does not state what an unauthorized or out-of-window attempt returns, nor explicitly that text edits are not recoverable, which keeps it just under a 5.

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?

The core action and the Slack exclusion are front-loaded, and the closing sentence usefully routes to two siblings. The middle is dense and run-on, with stacked parenthetical clarifications ('— a note or a plain message in an AccountHub chat —') that slow parsing, though no sentence is truly wasted.

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?

For a 5-parameter mutation tool with no output schema, the description covers permissions, per-field time limits, mode switching, replacement semantics and sibling routing. There is no output schema to explain, and an agent has enough to decide both whether to call it and how.

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 100% and the schema already documents each parameter including the null-clears and 'send mark_decided alone' constraints. The description adds some genuine semantics beyond the schema, notably that a supplied body replaces the whole text and that the time-limit rules vary by field, but this is incremental over an already-complete schema, so the baseline 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?

Opens with the specific verb and resource ('Edit the title, body or due date of an item'), immediately scopes it to AccountHub shared projects and explicitly excludes a Slack workspace. It also distinguishes the second mode (mark_decided) within the same sentence, so an agent can tell it apart from edit_chat_message or update_shared_project without opening a schema.

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

Usage Guidelines5/5

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

It names the alternatives by name and the condition that selects each: reassign_shared_item for changing who does the work, complete_shared_item for changing state, edit_chat_message for the analogous chat-text edit. It also states who may edit ('only the person who placed an item... and only while still a member') and lays out the per-item-type time limits, leaving little to inference.

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

All AccountHub toolsInspect
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.

Resources