Skip to main content
Glama
kerbelp

Metatron

by kerbelp
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

submit_candidate_decision

Record newly discovered engineering conventions as reviewable candidates, so maintainers can approve them before they become canonical for other agents.

Instructions

Record a new engineering convention you discovered while working — for human review.

    Call this when you find an undocumented convention, a tricky gotcha, or a preferred
    pattern that Metatron did not already know but future agents should. It is stored as
    an uncurated CANDIDATE: a human maintainer must approve it in the Metatron UI or CLI
    before it becomes canonical and is served to other agents. Nothing you submit here is
    auto-promoted.

    Returns the new candidate decision's id. If the pattern near-duplicates a decision
    already on record (in any wording), nothing new is stored and the existing
    decision's id is returned with a note — no need to resubmit known conventions.

Input Schema

NameRequiredDescriptionDefault
scopeYesWhere the rule applies: a file path, directory/glob, or architectural layer (e.g. "src/services/**"), or "global".
patternYesThe concrete rule or guideline, stated imperatively (e.g. "Use internal.http for outbound calls, not the requests library").
keywordsNoOptional: 3-8 retrieval terms an engineer might use when describing a task this rule applies to — synonyms and code identifiers not already in the pattern wording (e.g. ["s3", "presigned", "upload"]).
rationaleYesWhy the convention exists — the problem or bug it prevents (e.g. "flaky network caused phantom 5xx errors; the internal client retries").
confidenceNoHow strongly the team holds this convention.medium

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.13.1
    • addedInput schema / properties / keywords
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional: 3-8 retrieval terms an engineer might use when describing a task this rule applies to — synonyms and code identifiers not already in the pattern wording (e.g. [\"s3\", \"presigned\", \"upload\"]).",
+  "title": "Keywords"
+}
  2. Addedv0.3.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers: the submission is stored as an uncurated CANDIDATE, a human must approve before it becomes canonical, and nothing is auto-promoted. It also discloses dedup behavior (near-duplicate returns the existing id with a note), which is exactly the kind of life-cycle context an agent needs.

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?

Purpose and when-to-call are front-loaded, and the candidate/dedup mechanics follow logically. It is slightly longer than necessary — 'Nothing you submit here is auto-promoted' largely restates the preceding approval requirement — a minor redundancy.

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

Completeness5/5

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

An output schema exists, yet the description still aids the agent by stating that the new candidate id is returned and how the near-duplicate case resolves. Combined with the rich schema, nothing needed to call this tool correctly is missing.

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 pattern, scope, rationale, keywords, and confidence with good examples. The description adds no parameter-level syntax or format detail beyond what the schema provides, so the baseline of 3 is appropriate.

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 and resource — 'Record a new engineering convention you discovered while working' — and clarifies the target of the write (a candidate for human review). It is clearly distinguishable from read-oriented siblings like get_decisions_for_context and get_verification.

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?

Explicitly names the trigger conditions ('undocumented convention, a tricky gotcha, or a preferred pattern that Metatron did not already know') and adds a when-not condition by noting near-duplicates need no resubmission. Nothing about invoking this tool is left to inference.

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