evidence-log

Record the digest of a decision

record_evidence

Record the SHA-256 of a decision record you keep yourself, so it can later be shown to be unchanged. Send the digest and a short kind, never the record. Needs your RiskRouter key in the Authorization header of the MCP connection. Entries are permanent.

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": {
      "record_digest": "<record_digest>",
      "kind": "<kind>"
    },
    "name": "record_evidence"
  }
}

Input Schema

Name	Required	Description
`kind`	Yes	A short tag such as ai.decision.
`chain_seq`	No	Optional, with chain_tag: this record's position in its chain, from 1.
`chain_tag`	No	Optional: the completeness chain this record belongs to (64 hex characters derived from a secret you keep).
`record_digest`	Yes	SHA-256 of your salted record, lowercase hex. Never the record itself.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 7, 2026

addedInput schema / properties / chain_seq

Added value: +{
+  "description": "Optional, with chain_tag: this record's position in its chain, from 1.",
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / chain_tag

Added value: +{
+  "description": "Optional: the completeness chain this record belongs to (64 hex characters derived from a secret you keep).",
+  "pattern": "^[0-9a-f]{64}$",
+  "type": "string"
+}

First observedOct 1, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing three things the schema and hints do not: an auth requirement (RiskRouter key in the Authorization header), irreversibility ('Entries are permanent'), and a data-handling constraint ('never the record'). This is exactly the added behavioral context the annotations bar rewards.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the action and object, then the privacy constraint, then auth, then permanence. No sentence is redundant and none restates the title or name.

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?

Covers purpose, auth, permanence, and the critical input constraint for a write tool with no output schema. It does not say what is returned on success (receipt, sequence number, head reference) or cross-reference the chain/checkpoint siblings that consume these entries, which is the remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains record_digest, kind, chain_tag, and chain_seq. The description reinforces the meaning of the digest ('SHA-256 of a decision record you keep yourself') but adds no syntax or semantics for the two optional chain parameters. Baseline 3 applies.

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?

States a specific verb and resource ('Record the SHA-256 of a decision record') and immediately clarifies the object being recorded is a digest, not the record itself. This cleanly separates it from the sibling get_* tools, which retrieve proofs, heads, chains, and attestations rather than writing.

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 a clear motivation for when to use it: recording now so it 'can later be shown to be unchanged' (i.e., anchor first, verify later via the get_* siblings). It does not explicitly name alternatives or state when not to use it, so it stops short of full routing guidance.

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

All evidence-log 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?