Skip to main content
Glama
io.github.xngg1021/academic-research-kernel

io.github.xngg1021/academic-research-kernel

by xngg1021

decision_trace

Trace causal ancestry, basis dependencies, outcome corrections, and lifecycle state history for a decision to audit its evolution and provenance.

Instructions

Trace causal ancestry, basis dependencies, outcome corrections, and lifecycle state history for a decision.

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": {
      "ledger": "<ledger>",
      "decision_id": "<decision_id>"
    },
    "name": "decision_trace"
  }
}

Input Schema

NameRequiredDescriptionDefault
ledgerYesDecisionLedger export dictionary.
receiptsNoPhysical receipt registry keyed by receipt ID or payload SHA-256.
decision_idYesThe decision identifier to trace.
content_payloadsNoAuthorized base64 content by lineage entity ID; maximum total 10 MiB.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

No annotations exist, so the description carries the full disclosure burden. It usefully scopes what is traced (four distinct dimensions) but is silent on whether the operation is strictly read-only, whether it requires authorization for the receipts or content payloads, and what volume or limits apply beyond the schema note.

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 no filler and the key nouns up front. Dense jargon ('basis dependencies', 'outcome corrections') slightly reduces immediate parseability, but nothing is wasted.

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?

For a four-parameter trace tool with nested objects, no annotations, and no output schema, the description covers what is being traced but not what comes back or which inputs are optional in practice. It is adequate to identify the tool but thin for actually invoking it correctly.

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%, so the schema already documents ledger, receipts, decision_id, and content_payloads, giving a baseline of 3. The description adds only thematic color (corrections, lifecycle) and never clarifies the relationship between the traced dimensions and the optional receipts/content_payloads inputs.

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?

A specific verb ('Trace') plus a resource ('a decision') and four enumerated trace dimensions: causal ancestry, basis dependencies, outcome corrections, lifecycle state history. That is far more precise than a tautology, but it never names or contrasts the nearby lineage/evidence trace siblings, so an agent cannot rule out research_lineage_trace or claim_evidence_trace from the text alone.

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

Usage Guidelines2/5

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

No when-to-use context, no prerequisites, no exclusions, and no pointer to an alternative tool. The only guidance is implicit in the word 'Trace' – an agent must guess whether this is the right diagnostic versus decision_ledger_validate.

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