Skip to main content
Glama

AgentMart

by ai.ciphyr.agentmart
OverviewDiscussionsAdmin

List, redrive or purge dead letters

queue_dead
Destructive

A queue's dead letters (messages claimed max_attempts times without an ack): list them, redrive them back to the queue (ids, or all), or purge them.

Input Schema

NameRequiredDescriptionDefault
allNoredrive: every dead letter.
idsNoredrive: these messages.
afterNolist: next_after of the previous page.
limitNolist: how many (default 20).
queueYesQueue name: 1 to 64 characters from a-z 0-9 . _ -.
actionYeslist, redrive (back to the queue) or purge (delete).
instance_idYesUtility instance id from buy or list_utilities.
passport_tokenNoYour amp_ token, only if you have no app sign-in and cannot send a header.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "action": "list",
+    "instance_id": "que_exampleexampleexample2",
+    "limit": 20,
+    "queue": "jobs"
+  }
+]
    • changedInput schema / properties / passport_token / description
      Previous value: -"Your amp_ token, only if your app has no sign-in and cannot send it as an Authorization header."New value: +"Your amp_ token, only if you have no app sign-in and cannot send a header."
  2. Changed4 schema fields changed
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • changedInput schema / properties / passport_token / description
      Previous value: -"Your amp_ token, only if your client cannot send it as an Authorization header; leave it out when your MCP app signed in."New value: +"Your amp_ token, only if your app has no sign-in and cannot send it as an Authorization header."
    • addedInput schema / properties / passport_token / maxLength
      Added value: +200
    • removedInput schema / properties / passport_token / pattern
      Removed value: -"^amp_(?:s_)?[A-Za-z0-9_-]{43}$"
  3. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered; the description usefully adds that purge deletes and that redrive re-enqueues messages, and defines when a message becomes a dead letter. It omits irreversibility of purge, whether redrive resets the attempt counter, and any permission requirements.

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?

A single sentence that front-loads the resource definition before the three verbs, with no filler. The parenthetical definition of dead letters earns its space by removing ambiguity about which messages are affected.

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?

With no output schema, one would like to know what list returns (message fields, next_after pagination) — the description leaves that implicit through the 'after'/'limit' params. Given eight parameters and multiple modes, the definition is otherwise complete enough to call correctly.

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 each parameter already carries a description ('redrive: every dead letter', 'list: how many', 'list: next_after of the previous page'). The description's '(ids, or all)' hints at the either/or choice between the two redrive inputs but adds little else beyond the schema.

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?

States a specific resource (a queue's dead letters) with a precise definition of the condition that produces them, and enumerates the three supported operations (list, redrive, purge). It is clearly distinct from queue_ack/claim/nack/put siblings, which act on live messages rather than dead letters.

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

Usage Guidelines4/5

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

The action enum semantics ('redrive them back to the queue (ids, or all)' and 'purge') tell the agent which operation to pick for each intent, and the dead-letter definition tells it when this tool is the right one at all. It stops short of stating exclusions or pointing at an alternative tool for non-dead-letter queue work.

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

All AgentMart toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources