Skip to main content
Glama

hallux_report

Idempotent

Report identifiers a model produced that turned out not to exist. HALLUX verifies each against its registry and records only absent ones as attestations in the public hallucination ledger, which is how names graduate to phantom and get watched for squatting. Requires an API key.

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": {
      "identifiers": "<identifiers>",
      "model": "<model>"
    },
    "name": "hallux_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYes
identifiersYes
promptClassNo

Output Schema

NameRequiredDescriptionDefault
buyNo
noteNo
errorNo
billingNo
ignoredNo
messageNo
resultsNo
recordedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedOutput schema / properties / billing / properties / remaining / description
      Added value: +"Credits or free identifiers left; null on Team and Feed, which are not metered."
    • changedOutput schema / properties / billing / properties / remaining / type
      Previous value: -"integer"New value: +[
      +  "integer",
      +  "null"
      +]
  2. Changed3 schema fields changed
    • changedInput schema / properties / identifiers / items / properties / namespace / description
      Previous value: -"pkg.npm, pkg.pypi, pkg.crates, pkg.go, pkg.maven (group:artifact), pkg.nuget, pkg.rubygems, pkg.packagist (vendor/name), pkg.hex, pkg.pub, img.docker, repo.github (owner/repo), cite.doi"New value: +"Covered: pkg.npm, pkg.pypi, pkg.crates, pkg.go, pkg.maven (group:artifact), pkg.nuget, pkg.rubygems, pkg.packagist (vendor/name), pkg.hex, pkg.pub, img.docker, repo.github (owner/repo), cite.doi. Other dotted namespaces return verdict unknown with reason namespace_unsupported and are not charged."
    • removedInput schema / properties / identifiers / items / properties / namespace / enum
      Removed value: -[
      -  "pkg.npm",
      -  "pkg.pypi",
      -  "pkg.crates",
      -  "pkg.go",
      -  "pkg.maven",
      -  "pkg.nuget",
      -  "pkg.rubygems",
      -  "pkg.packagist",
      -  "pkg.hex",
      -  "pkg.pub",
      -  "img.docker",
      -  "repo.github",
      -  "cite.doi"
      -]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "properties": {
      +    "billing": {
      +      "additionalProperties": true,
      +      "properties": {
      +        "charged": {
      +          "type": "integer"
      +        },
      +        "remaining": {
      +          "type": "integer"
      +        },
      +        "tier": {
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "buy": {
      +      "type": "string"
      +    },
      +    "error": {
      +      "type": "string"
      +    },
      +    "ignored": {
      +      "type": "integer"
      +    },
      +    "message": {
      +      "type": "string"
      +    },
      +    "note": {
      +      "type": "string"
      +    },
      +    "recorded": {
      +      "items": {
      +        "additionalProperties": true,
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "results": {
      +      "items": {
      +        "additionalProperties": true,
      +        "properties": {
      +          "confidence": {
      +            "type": "number"
      +          },
      +          "evidence": {
      +            "additionalProperties": true,
      +            "type": "object"
      +          },
      +          "namespace": {
      +            "type": "string"
      +          },
      +          "reason": {
      +            "type": "string"
      +          },
      +          "recommendation": {
      +            "type": "string"
      +          },
      +          "risk": {
      +            "additionalProperties": true,
      +            "properties": {
      +              "level": {
      +                "type": "string"
      +              },
      +              "signals": {
      +                "type": "array"
      +              }
      +            },
      +            "type": "object"
      +          },
      +          "successor": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "value": {
      +            "type": "string"
      +          },
      +          "verdict": {
      +            "enum": [
      +              "exists",
      +              "deprecated",
      +              "absent",
      +              "phantom",
      +              "squat",
      +              "unknown"
      +            ],
      +            "type": "string"
      +          },
      +          "version": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "type": "object"
      +}
  3. Added

TDQS

B3.4/5.0
Behavior4/5

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

Adds real behavioral context beyond the annotations: entries land in a PUBLIC hallucination ledger, only absent identifiers are recorded (so false reports are filtered server-side), and names graduate to `phantom` and get watched for squatting — a reputational side effect an agent should know. Auth requirement is also stated. Minor gaps: no rate/batch limits and no mention that the call is idempotent, though annotations already cover that.

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?

Three tight sentences, purpose front-loaded, then mechanism, then prerequisite. Dense jargon ('attestations', 'graduate to phantom') adds cognitive load but each sentence carries information; nothing is filler.

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 needn't be explained, and the auth/behavior story is adequate. However, with three parameters and zero top-level schema coverage, leaving `promptClass` and `model` entirely unexplained makes the definition incomplete for correct invocation.

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

Parameters2/5

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

Top-level schema description coverage is 0%, and the description explains none of the parameters. Critically, `promptClass` (a 7-value enum) and `model` are never mentioned in the description, and only the nested `namespace`/`value`/`version` fields carry schema docs. The description does not compensate for the coverage gap.

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?

Opens with a specific verb+resource: report identifiers a model produced that do not exist, then names HALLUX's registry check and the public ledger write. The distinction from hallux_check (verify a name) is inferable from 'turned out not to exist' but is never made explicit against the sibling tools.

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?

Implies the usage context (you have candidate identifiers you believe are fabricated) and states the API-key prerequisite, but gives no explicit when-to-use vs. hallux_check, no when-not, and no guidance on whether to pre-verify before submitting.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources