Skip to main content
Glama
rupturetrace-mcp

rupturetrace-mcp

by Susan571

submit_host_round

Submit a JSON host-mode assessment round with label, confidence, rationale, scope, and all 12 relation checks; get the next prompt or final summary. Invalid rounds are rejected for correction.

Instructions

Submit your JSON answer for the current step of a host-mode assessment.

round_output must contain label (-2..2), confidence (0..1), rationale, assessment_scope='whole_claim' and checks (all 12 relations once, each with relation_id, status, reason, evidence[{kind, source, quote}]). Returns the next stage prompt, or the final summary once all steps are done. Invalid rounds are rejected without advancing, so you can fix and resubmit.

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": {
      "session_id": "<session_id>",
      "round_output": "<round_output>"
    },
    "name": "submit_host_round"
  }
}

Input Schema

NameRequiredDescriptionDefault
session_idYes
round_outputYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose meaningful behavior: invalid rounds are rejected without advancing state, resubmission is allowed, and a valid round returns either the next stage prompt or a final summary. Gaps remain around whether a valid submission is irreversible and how session state is scoped, but the core transactional semantics are covered.

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?

Short, front-loaded with the payload contract, then return behavior, then the rejection/retry rule. Every sentence adds information; the only cost is that the dense required-fields sentence is hard to parse in one read.

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 tool with a deeply nested payload, no output schema, and no annotations, the definition covers the nested contract, cardinality constraint (12 relations once each), and return behavior. What is missing is modest: how session_id is obtained, and the valid enumerations for status and evidence kind.

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

Parameters4/5

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

Schema coverage is 0% and round_output is an untyped object with additionalProperties, so the description is doing all the work — and it delivers: label range -2..2, confidence range 0..1, rationale, assessment_scope='whole_claim', and checks requiring all 12 relations exactly once with relation_id, status, reason, and evidence of {kind, source, quote}. Only session_id is left unexplained, and the permitted values for status/kind are not enumerated.

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 specific verb and resource: submitting a JSON round answer for the current step of a host-mode assessment, and notes the return is the next stage prompt or final summary. This clearly separates it from start_host_assessment and the assess_claim(s) siblings, though the term 'host-mode assessment' is never defined for an agent that lands here cold.

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?

Implied sequencing is present ('current step', 'all steps are done'), which tells an agent this is a mid-workflow call, and the rejection note encourages fix-and-resubmit. However, no alternative tool is named (e.g., when to use diagnose_rounds instead of resubmitting), and there is no explicit statement of prerequisites such as needing a session from start_host_assessment.

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