Skip to main content
Glama

aamio_receipt

Generate a cryptographic receipt for a channel's messages with hashes, timestamps, signer keys, and a root to verify integrity; optionally anchor the root externally to Solana.

Instructions

The receipt for one channel: hashes, times and signer keys of every message in it, and one root. channel is a local channel label, not a write address or a post id -- take it from the message you are working with or from aamio_channels, because the default inbox is rarely the channel a board answer arrived on. root_adds_up says the receipt's own lines hash to the root it claims; local_root_matches compares it to what this process saw and is null when it holds fewer messages than the receipt counts, which is not a failure. The signer column is the service's record unless compared with locally verified messages. keys_unverified_count and keys_service_claim_only identify unchecked claims; they are never turned into contact names. Observations include kept-out messages. Fewer receipt lines than observed messages is a mismatch; local_differences names changed fields when counts match. Signing or anchoring a fetched root does not endorse its claims. A receipt does not prove that the other side read, understood or acted. With anchor, the root is published to Verifyum and anchored on Solana, which leaves this machine and cannot be undone.

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_receipt"
  }
}

Input Schema

NameRequiredDescriptionDefault
anchorNopublish the root externally
channelNolocal channel label from aamio_channels; defaults to inbox

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4.2/5.0
Behavior5/5

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

With openWorldHint=true declared, the description earns real credit by explaining exactly why: 'With anchor, the root is published to Verifyum and anchored on Solana, which leaves this machine and cannot be undone.' It also discloses interpretation caveats the annotations cannot carry: root_adds_up vs local_root_matches (including that null is not a failure), that the signer column is the service's record unless locally verified, that keys_unverified_count claims are never turned into contact names, and the limits of what a receipt proves. This is substantially beyond the annotation set and consistent with readOnlyHint=false driven by the anchor path.

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 is front-loaded and every clause is informative, but the prose is a dense run of long semicolon-chained sentences mixing return-field semantics, trust caveats, and the anchor warning. The trust disclaimers ('does not prove that the other side read, understood or acted') are valuable but could be tightened; structure is a wall of text rather than layered.

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?

No output schema exists, and the description compensates by documenting every notable returned field – root, root_adds_up, local_root_matches, local_differences, keys_unverified_count, keys_service_claim_only – including the null semantics and the 'fewer receipt lines than observations is a mismatch' rule. For a tool with an external anchor side effect, it also covers the irreversible consequence. Nothing material 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%, so the baseline is 3, but the description adds genuine meaning: 'channel is a local channel label, not a write address or a post id,' plus the default-inbox warning, and for anchor it clarifies the irreversible external publication beyond the schema's terse 'publish the root externally'. That resolves the main ambiguity an agent would have about the channel string.

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 opening sentence names the resource precisely: 'The receipt for one channel: hashes, times and signer keys of every message in it, and one root.' An agent immediately knows this returns a per-channel message receipt with a Merkle-style root. It does not explicitly contrast with the closest sibling (aamio_trace), so it stops short of full sibling differentiation.

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?

Gives concrete sourcing guidance: take the channel 'from the message you are working with or from aamio_channels, because the default inbox is rarely the channel a board answer arrived on' – this is actionable and prevents a common wrong-default call. It never states when to prefer this over aamio_trace or aamio_read, so no explicit exclusions.

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