TunnelMind Data API

agent_record

Spec 125. One agent public key's record across attested tollbooth sites: summed requests, a sample of paths, whether robots.txt was fetched, the signed snapshots each figure comes from (sources[]), and the newest 100 receipts naming the key, verbatim. Free, no auth. Facts, not verdicts: no score, no tier, no IP. Counts are a LOWER BOUND. The cache is not the record — verify says how to recompute every sum from tollbooth_export and check each source's sig.

Use this tool when:

You want what the commons has observed of a specific agent key.
You are auditing an agent's conduct and want to check it yourself.

Returns:

key, ua, requests, isolates, first_seen, last_seen, paths[] (capped), robots_txt_fetched.
sources[]: {site, isolate_id, seq, taken_at, sig}.
paid, receipts_total, receipts[] (each receipt verbatim as signed), plus the honesty fields.
404 for a key with nothing attested: the same record, empty, in error.record.

Cost:

Free. Anonymous 10/min per IP, no daily cap.

Latency:

Typical: <150ms.

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": {
      "key": "<key>"
    },
    "name": "agent_record"
  }
}

Input Schema

Name	Required	Description	Default
`key`	Yes	Agent Ed25519 public key, 43-character base64url (no padding).

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses that counts are a LOWER BOUND, that the cache is not the record, that 404 means an empty record returned in `error.record` rather than a failure, plus free/no-auth access, a 10/min per-IP rate limit with no daily cap, and sub-150ms typical latency. It also discloses what is deliberately absent (scores, tiers, IPs).

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 description is front-loaded with purpose, then cleanly sectioned into use cases, returns, cost, and latency — easy to scan. It is somewhat long with repeated assurances ('Facts, not verdicts', 'Counts are a LOWER BOUND', 'The cache is not the record') that could be tightened, but each still carries distinct information.

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 one-parameter read tool with no annotations and no output schema, the description supplies everything an agent needs: the exact return fields including nested `sources[]` shape, error semantics, rate limits, latency, and a provenance caveat about recomputation. Nothing material is left to inference.

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 the schema already specifies the 43-character base64url Ed25519 key pattern, so the baseline is 3. The description adds meaning beyond the schema by framing `key` as the identity whose cross-site observation record is returned and by specifying the unknown-key behaviour (404 with an empty record), which the schema does not cover.

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 opening states a specific resource and scope: one agent key's record across attested tollbooth sites, enumerated as summed requests, sampled paths, robots.txt status, signed sources, and receipts. It also draws a sharp boundary against adjacent tools by declaring 'Facts, not verdicts: no score, no tier, no IP,' distinguishing it from score/verdict siblings.

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?

Two explicit 'Use this tool when' bullets give concrete selection contexts (observing a key, auditing conduct). It routes to alternatives for the recompute job — `verify` and `tollbooth_export` — but never states when NOT to use it, e.g. versus verify_agent or tollbooth_agents, which are close neighbours by name.

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

All TunnelMind Data API tools Inspect

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

Need Help?