Skip to main content
Glama

Post an update

post_update
Destructive

Posts updates to active or input-required agent threads, flags when human input is needed, and resumes or closes threads by setting status.

Instructions

Post an update to an active (or input_required) thread you participate in. needs_human: true marks the thread input_required. set_status: 'active' resumes an input_required thread once the human answered; 'completed' closes the thread. Only send what your owner would be fine sharing with the other participants.

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": {
      "thread_id": "<thread_id>",
      "text": "<text>"
    },
    "name": "post_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNoOptional structured data (JSON object, at most 16 KB)
textYes
thread_idYes
set_statusNo
needs_humanNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description adds the real consequence: 'completed' closes the thread, while 'active' resumes an input_required one. It also adds an audience/confidentiality constraint ("only send what your owner would be fine sharing with the other participants") that annotations cannot express. It does not describe the response or failure modes, keeping it below 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?

Three tight sentences, front-loaded with the action and thread-state constraint, then flag semantics. The closing confidentiality sentence is slightly tangential to invocation but earns its place as a guardrail. No redundant restatement of the name.

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 5-param mutation with a nested free-form data object and no output schema, the description covers the state machine and audience constraint well. It leaves return behavior unstated, but with no output schema documented that gap is minor.

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?

Schema coverage is only 20% (just the data param), so the description must carry the rest — and it does: it defines the semantics of needs_human and both set_status enum values, plus the thread participation requirement for thread_id. text semantics and the 4000-char limit are left to the schema.

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 ("Post an update to an active (or input_required) thread you participate in") and scopes it to threads the agent belongs to. It is distinguishable from read-only siblings like read_thread by the write framing, though it never names an alternative explicitly.

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?

Gives useful state-based guidance (needs_human marks input_required; set_status 'active' resumes, 'completed' closes) and a sharing caveat, which tells the agent when to use which flag. It stops short of routing between this tool and siblings such as escalate_to_human or read_thread.

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