Skip to main content
Glama
Sign In

LLPRO Campus

by ai.llpro
OverviewDiscussionsAdmin

Check a long run's records signed by someone other than the agent, with a heartbeat on a clock. Agent transcripts and telemetry are not evidence

run_record_verify
Read-onlyIdempotent

Check a long run's records signed by a key the records say is not the agent's (a host, runner or supervisor: the recorder), with a heartbeat on a clock. Send the records in order: each {v 1, type run-record, run_id, seq, kind start|heartbeat|event|end, at, prev, recorder_id, recorder_key, sig} chained by SHA-256; the start record names agent_id and heartbeat_s. Get back valid or invalid (signatures, chain, order), every check, heartbeat_kept, the run state (ended, running or silent), missed beats, and a summary signed by LLPRO with the time we saw it, checkable offline. Agent transcripts and telemetry are untrusted: carry only their SHA-256 as telemetry_hash. Pin expected_agent, expected_recorder and expected_head for the strongest result. We do not keep the records. It does not show who the recorder is or that the records are complete. Not an audit opinion, not a certification, not a qualified timestamp, not evidence of compliance. Free. Feeds the standards and regulatory road: run logs signed by someone other than the agent.

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": {
      "records": "<records>"
    },
    "name": "run_record_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
recordsYes
expected_headNothe recorder's latest chain head you know of; if the last record sent is not it, the result is invalid (catches dropped newest records)
expected_agentNothe agent public key you expect; if it differs (or the start record names none) the result is invalid
expected_recordsNothe number of records you know exist; if a different number is sent the result is invalid
expected_recorderNothe recorder public key you trust; if it differs the result is invalid

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond readOnly/idempotent/non-destructive annotations, it discloses statelessness ('We do not keep the records'), the full result shape (valid/invalid over signatures, chain, order; heartbeat_kept; run state; missed beats; an offline-checkable LLPRO-signed summary with observation time), and honest limits ('does not show who the recorder is or that the records are complete'). Nothing contradicts 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 purpose is front-loaded and nearly every clause carries operational information, including the inline record shape that saves a schema dive. It is one dense run-on paragraph with a stray fragment ('Free.') and a four-item negation list, so readability is slightly below what the content deserves.

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 complex cryptographic verification tool with no output schema, the description covers input ordering, chaining, optional pinning, the returned fields, offline verification of the summary, and explicit non-guarantees. An agent has enough to call it correctly and to report results honestly.

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?

With 80% schema coverage the baseline is 3, but the description adds real meaning: records are SHA-256 chained, the start record carries agent_id and heartbeat_s, and expected_agent/expected_recorder/expected_head exist to 'strengthen' the result. It also gives the practical reason telemetry must be supplied only as a hash. It does not explain expected_records, so one optional parameter is left to the schema alone.

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 states a specific verb and resource: check a long run's records that are signed by a recorder key which the records themselves say is not the agent's, plus a heartbeat-on-a-clock check. That framing distinguishes it functionally from agent-key oriented siblings (agent_identity_check, countersign_verify) by insisting the signer is not the agent. It never names an alternative tool, so it stops short of the 5 anchor.

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?

It tells the caller to send records in order and to 'pin expected_agent, expected_recorder and expected_head for the strongest result', which is concrete usage advice for optional params. It also declares what the output is not (audit opinion, certification, qualified timestamp, compliance evidence), scoping interpretation. There is no explicit when-to-use-this-instead-of-X routing among the sibling check tools.

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

All LLPRO Campus toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources