Skip to main content
Glama

aamio_pending

Read-onlyIdempotent

Lists sent messages whose delivery outcome is unsettled so you can retry or forget them instead of resending duplicates.

Instructions

Messages this runtime sent whose fate is not settled: working on the proof of work an inbox asked for, still in flight, or unknown because no answer came back before the process stopped. Unknown does not mean undelivered. If one of these matters, settle it here rather than sending the same request again: aamio_outbox_retry sends the stored bytes for one id, and aamio_outbox_forget stops waiting for one. Never compose a replacement for a message whose outcome is unsettled.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "aamio_pending"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish that this is a safe, idempotent, non-destructive read. The description adds real interpretive context the annotations cannot: the three pending states and the caveat that 'unknown' does not mean undelivered, which prevents an agent from wrongly assuming failure. It doesn't describe volume, ordering, or whether message bodies are included, so not 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?

Front-loaded with the definition of the pending set, then the corrective guidance, then the hard rule. Every sentence carries information; the only density cost is that the first sentence packs three states into a clause that takes a second read.

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 zero-parameter read with no output schema, the description covers what the set contains, how to interpret the ambiguous case, and what to do next. The remaining gap is the shape of the returned entries, which an agent must discover at call time.

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?

The tool takes zero parameters, so the schema imposes no semantic burden and the baseline is 4. The description correctly requires no argument discussion, though it does imply results carry ids usable with aamio_outbox_retry and aamio_outbox_forget.

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?

The description defines the resource precisely: messages this runtime sent whose fate is unsettled, enumerated as three concrete states (awaiting proof of work, still in flight, unknown after process stop). It is clearly distinct from the retry/forget siblings. It never uses an explicit verb like 'list' or 'returns', which keeps it just short of a 5.

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?

Strong routing guidance: when one of these matters, settle it here and the two named alternatives (aamio_outbox_retry for stored bytes, aamio_outbox_forget to stop waiting) are given with their distinct purposes. It also adds a prohibition against composing a replacement. What's missing is the moment to call this tool itself (e.g., before resending, after a restart), which is only implied.

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