Skip to main content
Glama

Nomos - Deterministic Git & AST Governance for AI Coding Agents

Inspect Nomos Gate or ERR_* Failure Remediation

diagnose_nomos_error
Read-onlyIdempotent

Look up any Nomos ERR_* failure code, TC-AGT-* vector, or nomos verify gate rejection to retrieve its root cause and non-bypassing AST remediation. Example: error_code='ERR_CROSS_PLANE_MUTATION' returns the remediation guide. Use when troubleshooting a verify failure or pre-commit hook error. Do NOT use when browsing the full catalog of 42 gates by Law or category without an error (use inspect_dod_gates instead).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "error_code": "ERR_CROSS_PLANE_MUTATION"
    },
    "name": "diagnose_nomos_error"
  }
}

Input Schema

NameRequiredDescriptionDefault
error_logNoOptional raw error message, gate name, or pre-commit output snippet.
error_codeNoOptional ERR_* identifier such as ERR_CROSS_PLANE_MUTATION or ERR_COGNITIVE_DEBT.

Output Schema

NameRequiredDescriptionDefault
queryYesCombined error query string.
docsUrlYesGate catalog documentation URL.
summaryYesDeterministic Markdown remediation summary.
canonicalUrlYesCanonical gate reference URL.
matchedCodesYesMatched ERR_* diagnostics.
matchedGatesYesRelated compiled gates.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuine behavioral context by promising a 'non-bypassing AST remediation' and root-cause output rather than just a code lookup, but it does not mention what happens when both parameters are omitted or how the two inputs are combined.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the lookup scope, followed by a compact example, then usage, then the exclusion. Every sentence carries distinct information and nothing is repeated from the schema or annotations.

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?

An output schema exists, so return values need no elaboration, and the description covers scope, example input, and routing. The only remaining gap is guidance on supplying zero versus one versus both of the optional parameters for a tool with required-count 0.

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 100%, so the baseline would be 3; the description goes further by showing a worked error_code lookup and implying error_log accepts raw pre-commit output snippets in the diagnostic flow. It still leaves the interaction between the two optional inputs (either alone? both together? neither?) unstated.

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?

States a specific verb ('look up') and precise resources (Nomos ERR_* failure codes, TC-AGT-* vectors, nomos verify gate rejections) plus what is returned (root cause and non-bypassing AST remediation). The named example error_code='ERR_CROSS_PLANE_MUTATION' makes the resource concrete, and the exclusion of inspect_dod_gates separates it from the nearest sibling.

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

Usage Guidelines5/5

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

Gives an explicit when ('troubleshooting a verify failure or pre-commit hook error') and an explicit when-not ('browsing the full catalog of 42 gates by Law or category without an error'), naming inspect_dod_gates as the alternative for that case. This is the strongest possible routing guidance.

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.