Skip to main content
Glama
john-broadway

Proximo

by john-broadway
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

audit_verify

Read-only

Verifies an audit chain read-only, reports the first break, checks an expected head to catch a cut tail, and validates a sealed archive beside the ledger.

Instructions

READ-ONLY: walk the chain and report the first break; expected_head catches a cut tail; path= verifies a sealed archive beside the ledger.

Input Schema

NameRequiredDescriptionDefault
pathNo
expected_headNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.46.2
    • addedInput schema / properties / expected_head / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedInput schema / properties / expected_head / description
      Removed value: -"64-char hex head() value pinned off-box; verifying against it also catches tail truncation, a forged tail-append, or a full ledger replacement. Omit to fall back to PROXIMO_AUDIT_EXPECTED_HEAD."
    • addedInput schema / properties / expected_head / title
      Added value: +"Expected Head"
    • removedInput schema / properties / expected_head / type
      Removed value: -[
-  "string",
-  "null"
-]
    • addedInput schema / properties / path
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Path"
+}
    • addedInput schema / title
      Added value: +"audit_verifyArguments"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "audit_verifyDictOutput",
+  "type": "object"
+}
  2. Changed4 schema fields changedv0.31.1
    • removedInput schema / properties / expected_head / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • removedInput schema / properties / expected_head / title
      Removed value: -"Expected Head"
    • addedInput schema / properties / expected_head / type
      Added value: +[
+  "string",
+  "null"
+]
    • removedInput schema / title
      Removed value: -"audit_verifyArguments"
  3. Changed1 schema field changedv0.21.0
    • addedInput schema / properties / expected_head / description
      Added value: +"64-char hex head() value pinned off-box; verifying against it also catches tail truncation, a forged tail-append, or a full ledger replacement. Omit to fall back to PROXIMO_AUDIT_EXPECTED_HEAD."
  4. First observedv0.18.1

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, so the leading 'READ-ONLY' earns nothing, but the description adds real behavior: it reports the *first* break (not all breaks) and detects a truncated tail via expected_head. It does not state whether a break is surfaced as an error or a result value, which is the main remaining gap.

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?

A single front-loaded sentence with the read-only flag first and each clause earning its place. The compressed '=' shorthand and semicolon chaining make it slightly cryptic but nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, and both optional parameters get a mention. Still, for a verification tool the definition leaves unclear what a successful verification looks like and whether a detected break raises an error, which an agent needs to call it confidently.

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 0%, so the description carries the burden and does explain both parameters' intent (expected_head for tail-cut detection, path for a sealed archive beside the ledger). It is still telegraphic: no indication of whether path is a file or directory, nor what format expected_head takes as a hash.

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?

States a concrete operation: walk the chain and report the first break, i.e. verify ledger chain integrity. The verb+resource are specific and distinguishable from audit_entries (which presumably lists), though the description never names that sibling or defines what 'the chain' refers to.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The two parameter clauses imply usage scenarios ('expected_head catches a cut tail', 'path=<archive> verifies a sealed archive'), which is useful when-to-use guidance. However it never says when to skip verification, when to prefer audit_entries, or what the default no-parameter call covers.

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

Deploy Server

Other Tools