Skip to main content
Glama
krusch-frontend-mcp

krusch-frontend-mcp

by kruschdev

frontend_get_provenance

Read-onlyIdempotent

Trace a frontend RAG item's version history to uncover why a design rule or context exists.

Instructions

Company Brain Substrate (SQLite): Interrogate why a piece of context or design rule exists by tracing its version history.

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": {
      "id": "<id>"
    },
    "name": "frontend_get_provenance"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe ID of the frontend RAG item to trace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that the trace goes through version history stored in a SQLite substrate, which is genuine extra context, but it says nothing about how deep the history goes, whether missing IDs error or return empty, or what the trace looks like.

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 sentence that front-loads the action and purpose with no redundant restatement of the name. The 'Company Brain Substrate (SQLite):' prefix is the only wasted token, since storage engine detail rarely helps tool selection.

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 one-parameter, read-only, idempotent tool with full schema coverage and annotations, the selection-relevant information is mostly present. The gap is that no output schema exists and the description never indicates what a provenance trace returns (versions, timestamps, diffs, authors), which is the main thing an agent would need to use the result.

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%, and the single 'id' parameter is documented as 'The ID of the frontend RAG item to trace'. The description adds only marginal meaning by clarifying that the item may be a piece of context or a design rule; with the schema doing the heavy lifting, the baseline 3 applies.

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: tracing the version history of a frontend RAG item (context or design rule) to explain why it exists. This is clearly distinguishable from graph traversal or rule querying siblings, though the 'Company Brain Substrate (SQLite)' prefix adds noise rather than clarity.

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?

Usage is implied by the phrase 'Interrogate why a piece of context or design rule exists', which suggests reaching for this when provenance or rationale is needed. However, there is no explicit when-to-use/when-not guidance and no sibling alternative named (e.g., query_design_rules) for the case where the agent only wants the current rule rather than its history.

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