Sairen

manage_dead_letter

Park failed task payloads in a dead-letter queue for multi-agent swarms, letting recovery agents lease, inspect, and retry failed runs while tracking acknowledgments and retries.

Instructions

    [Cost: $0.0010 USDC on Base & Solana] Ephemeral Dead-Letter Queue and Error Vault for Multi-Agent Swarms.
    
    Keywords: dead letter queue, dlq, failure buffer, retry queue, poison pill queue.
    Parks failed task execution payloads, allows recovery supervisor agents to lease/inspect failed runs,
    and manages retry lifecycles (ack/nack).

    Actions:
    - 'push' : Park a failed tool execution (requires tool_name, error_message, payload).
    - 'pop'  : Lease the oldest failed task for recovery/replay.
    - 'peek' : Inspect failed tasks in the queue without dequeuing.
    - 'ack'  : Acknowledge successful recovery of a task (removes from DLQ).
    - 'nack' : Report retry failure (increments retry count; marks dead if limit reached).
    - 'stats': Get queue health, depth, and failure reason aggregates.
    - 'clear': Purge expired or resolved items from the queue.

Input Schema

TableJSON Schema

Name	Required	Default
`limit`	No
`action`	No	push
`payload`	No
`task_id`	No
`tool_name`	No	unknown
`error_type`	No	UnknownError
`queue_name`	No	default
`max_retries`	No
`ttl_seconds`	No
`error_detail`	No
`error_message`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.3.1Sep 30, 2026

TDQS

A3.8/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden and mostly does: it discloses side effects that matter for a mutation tool (ack removes the item, nack increments retry count and marks dead at the limit, clear purges expired/resolved items) plus ephemerality and cost. It omits auth/permission requirements, concurrency/lease behavior, and rate limits, so it is not complete.

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

Conciseness3/5

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

Purpose and action list are front-loaded and the action bullets are efficiently structured, but the 'Keywords:' line is SEO padding that earns no place in an agent-facing definition, and the cost banner consumes the first line. Net structure is serviceable but not tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The action list gives good operational coverage and an output schema exists so return values need not be explained. However, for an 11-parameter, zero-annotation mutation tool, the description leaves most parameters and all permission/lease semantics unexplained, which is a real gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% across 11 parameters, so the description must compensate and largely does not. It references only tool_name, error_message and payload (for 'push'), leaving task_id, queue_name, max_retries, ttl_seconds, error_type, error_detail, limit and action undocumented anywhere; the required-parameter statement also conflicts with a schema that marks nothing required.

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 verb+resource: managing a Dead-Letter Queue / error vault for multi-agent swarms. It is unambiguously distinguishable from every sibling (none of which handle DLQ semantics), and the one-line summary 'Parks failed task execution payloads... manages retry lifecycles' pins down the domain.

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?

Names the intended caller ('recovery supervisor agents') and the action list effectively tells the agent which operation to pick for which scenario (push to park, pop to replay, peek to inspect, stats for health). There is no explicit when-not or alternative-tool guidance, but with no overlapping siblings that gap is minor.

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

Deploy Server