Skip to main content
Glama

aamio_outbox_retry

Retry sending one unsettled message by its message_id using the exact stored bytes, without sweeping other messages; the response tells you if it was resent or refused permanently.

Instructions

Send one unsettled message again, exactly the bytes that were stored. id is the message_id from a send whose outcome was unknown, or from aamio_pending, and it is required: settling one is a decision per message and never a sweep. The bytes are the same ones, so a recipient that keeps what it has seen marks the second copy as a replay; one reading with raw HTTP, or with a library that keeps no such record, marks nothing, and identical bytes alone do not make a delivery happen once. Whether the action behind the message is safe to repeat is your agreement with the other side and not this tool's: a message whose recipient or meaning has changed must not go out under the old id, so leave it and send a new one that says what it is. A message aamio refused for a reason that will not change is not sent again, and the answer says which of those it was.

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": {
      "id": "<id>"
    },
    "name": "aamio_outbox_retry"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesthe message_id of one unsettled message

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.6.36
    • addedInput schema / properties / id / maxLength
      Added value: +64
    • addedInput schema / properties / id / minLength
      Added value: +1
  2. Addedv0.6.32

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare idempotentHint=false, but the description goes further and explains the consequence: identical bytes mean a deduplicating recipient records a replay while a raw-HTTP reader records nothing, so identical bytes do not produce exactly-once delivery. It also places the safety of repeating the underlying action on the caller, and says the response distinguishes retryable from permanently refused cases, none of which is in the annotations.

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 its scope are front-loaded in the opening clause and every sentence carries information, with no filler. It loses a point because several sentences, especially the replay/dedup passage, are syntactically dense enough to require a second read.

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 single-parameter tool with no output schema, the description supplies the preconditions, the failure modes, and the shape of the answer (which of the two outcomes occurred). Nothing an agent needs before calling it, or to interpret the result, is missing.

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 100% and there is a single documented parameter, so the baseline is 3. The description earns above baseline by specifying the provenance of the id (a send whose outcome was unknown, or aamio_outbox/pending listing) and the invariant that it must identify a still-unsettled message.

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?

The first sentence gives a precise verb and resource: send one unsettled message again, using exactly the stored bytes. That framing is distinguishable from aamio_send (compose something new) and from aamio_pending (list, not act), both of which the text references by name or implication.

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 where the id comes from (a send with unknown outcome, or aamio_pending), that settling is per-message and never a sweep, and two explicit exclusions: a message whose recipient or meaning has changed must be left and a new one sent instead, and a message refused for a permanent reason is not retried. That is when, when-not, and the alternative in one place.

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