Vigil — an outside witness for AI agents

vigil_verify_lease

Read-onlyIdempotent

Offline, FAIL-CLOSED check of a lease token against a mandatory, independently pinned Ed25519 public key. Returns allow=true only for a valid signature before expiry and recheck_by_ms. It does not authenticate the calling agent, enforce action/amount policy, or query live revocation; a customer gateway must do those checks before every provider action. Checks signature, expiry and the signed recheck deadline only. It does not check live revocation, agent identity, action, amount or gateway policy; those checks are mandatory at the gateway.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`lease`	Yes	A full lease token from vigil_grant_lease.
`pubkey_hex`	Yes	Mandatory Ed25519 public key pinned from a trusted out-of-band source; never copy it from the lease.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 14, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
- addedInput schema / properties / pubkey_hex / description
```
Added value: +"Mandatory Ed25519 public key pinned from a trusted out-of-band source; never copy it from the lease."
```
- 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: -[
-  "lease"
-]New value: +[
+  "lease",
+  "pubkey_hex"
+]
```
First observedSep 6, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations already mark the tool read-only, idempotent, and non-destructive; the description adds valuable behavioral context: offline execution, fail-closed semantics, expiration and recheck_by_ms constraints, and the explicit lack of live revocation or policy enforcement. No contradiction exists between description and annotations.

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?

The description is front-loaded with purpose and key behavior, but it repeats the same limitation list twice: once in the second sentence and again in the final sentence. The redundancy makes it less concise than it could be, though it remains structured and readable.

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?

Given the two simple parameters, the rich annotations, and the explicit success condition of allow=true, the description provides enough context to invoke the tool correctly. It could be more complete by stating the exact failure/error response shape, especially since there is no output schema, but this is a minor 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%, with lease and pubkey_hex already well documented, including the warning to never copy the key from the lease. The description reinforces the independently pinned key concept but adds little semantic value beyond the schema, so the baseline score of 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 names a specific verb and resource: an offline, fail-closed check of a lease token against a pinned Ed25519 public key. It clearly distinguishes this from receipt verification and gateway policy checks, and states the exact success condition.

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 clearly states what this tool is for and what it must not be used for, explicitly listing missing checks such as live revocation, agent identity, action, amount, and gateway policy. It does not name specific sibling tools as alternatives, but the context of mandatory gateway checks provides clear usage boundaries.

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?