Vigil — an outside witness for AI agents

vigil_verify_receipt

Read-onlyIdempotent

Verify a receipt's hash and Ed25519 signature against a mandatory, independently pinned Ed25519 public key. The key must not come from the receipt being checked. Returns valid=false for tampering, forgery, a wrong signer, or malformed input. Read-only and local to Vigil.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`receipt`	Yes	A full receipt object as returned by vigil_notarize / vigil_get_receipt.
`pubkey_hex`	Yes	Mandatory Ed25519 public key pinned from a trusted out-of-band source; never copy it from the receipt.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 14, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / pubkey_hex / description

Previous value: -"The signer's pubkey to check against, confirmed out-of-band. If omitted, checks against this server's own key (self_attested)."New value: +"Mandatory Ed25519 public key pinned from a trusted out-of-band source; never copy it from the receipt."

addedInput schema / properties / pubkey_hex / maxLength
```
Added value: +64
```
addedInput schema / properties / pubkey_hex / minLength
```
Added value: +64
```
addedInput schema / properties / pubkey_hex / pattern
```
Added value: +"^[0-9a-f]{64}$"
```

changedInput schema / required

Previous value: -[
-  "receipt"
-]New value: +[
+  "receipt",
+  "pubkey_hex"
+]

First observedSep 6, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, and non-destructive. The description adds meaningful behavior: 'Read-only and local to Vigil' and the exact failure modes that produce valid=false (tampering, forgery, wrong signer, malformed input). This goes beyond the annotations and clarifies outcome semantics.

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?

Three sentences carry everything: verification target, key requirement, failure behavior, and read-only locality. Every sentence earns its place and the critical security constraint is front-loaded.

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 two-parameter read-only verification tool, the description covers invocation-wise preconditions, failure semantics, and behavior. The only minor omission is an explicit description of the success return (valid=true), though this is strongly implied by the false-case enumeration. No output schema exists, so the description carries the return contract reasonably well.

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?

The schema already provides 100% coverage with detailed parameter descriptions, including the 'independently pinned' and 'never copy it from the receipt' guidance. The description's mention of the key requirement is redundant. No additional meaning is added beyond what the schema already documents, so a baseline 3 is appropriate.

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 description states exactly what the tool does: verify a receipt's hash and Ed25519 signature against a pinned public key. It names the resource ('receipt') and the operation ('verify') with enough specificity to distinguish it from sibling tools like vigil_verify_lease and vigil_verify_source.

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?

The description gives clear usage context: the key must be mandatory, independently pinned, and must not come from the receipt being checked. It does not explicitly name alternatives or exclusions, but the domain-specific wording makes it obvious this is for verifying receipts rather than leases or sources.

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

All Vigil — an outside witness for AI agents 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?