Skip to main content
Glama

dismiss_thread

DestructiveIdempotent

Soft-close abandoned, superseded, or no-longer-relevant threads without marking them complete. Use it to retire stale work while retaining history and optionally saving a dismissal note.

Instructions

Soft-close a thread that should stop without being marked complete.

    Use for abandoned, superseded, or no-longer-relevant work. Use mark_done
    when the intended outcome was completed, or pause_thread when it will be
    resumed later. Prefer confirm_thread_relevant / snooze_thread_triage for
    a calm stale-work check — never auto-dismiss from those tools.
    

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>"
    },
    "name": "dismiss_thread"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoOptional short dismissal explanation saved when the status changes.
thread_idYesExact thread ID to soft-close as abandoned or superseded; retains its history.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.22.0
    • addedInput schema / properties / note / description
      Added value: +"Optional short dismissal explanation saved when the status changes."
    • addedInput schema / properties / thread_id / description
      Added value: +"Exact thread ID to soft-close as abandoned or superseded; retains its history."
  2. First observedv0.12.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, openWorldHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds real value by characterizing the operation as a "soft-close" that stops the thread rather than completing it, which is context the hints cannot convey. What it omits is the meaning of "soft" in practical terms: whether the state change is reversible, how to undo a dismissal, and whether a note is needed to make the action auditable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the core definition before enumerating alternatives, then closing with a misuse guardrail. Each sentence carries distinct routing information and nothing is repeated from the schema or annotations.

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?

An output schema exists, so return values need no prose, and annotations cover the destructive/idempotent profile. The definition is sufficient to select and call the tool correctly. The remaining gap is behavior after the call, specifically reversibility of a soft-close and any cross-scope effects implied by openWorldHint=true.

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 description coverage is 100%, and the schema already explains that note is an optional dismissal explanation saved on the status change and that thread_id is the exact ID retaining history. The description adds essentially no parameter-level meaning beyond that. The baseline 3 is correct because the schema carries this dimension entirely.

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?

"Soft-close a thread that should stop without being marked complete" names a specific verb (soft-close) and resource (thread), and immediately carves out the boundary against marking complete. The final clause distinguishing abandoned/superseded/no-longer-relevant work further pins the intent, so an agent can separate this from mark_done or pause_thread without opening any 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 states the enabling condition (abandoned, superseded, or no-longer-relevant work) and then names the exact alternatives with their selecting conditions: mark_done when the outcome was completed, pause_thread when it will be resumed. It even adds a negative guardrail, "never auto-dismiss from" confirm_thread_relevant / snooze_thread_triage, which prevents a plausible misuse pattern.

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