Skip to main content
Glama
Sign In
codelattice

codelattice

by aiulms
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

codelattice_workflow

Read-onlyIdempotent

Routes natural-language coding intent to the correct MCP action, guiding tool selection for project exploration, issue diagnosis, pre-edit review, and impact analysis.

Instructions

AI intent router and orchestration layer. Use this FIRST when unsure which CodeLattice tool or root to call. Use ask for natural-language routing, explore for progressive project/workspace orientation, diagnose_issue for symptoms, and before_edit only once you have a concrete target.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
modeNoWorkflow scenario / intent. ask routes a natural-language question; explore classifies root and recommends depth; before_edit routes to concrete review guidance.onboarding
nameNoAlias for symbol in explain_symbol flows
rootNoProject or workspace root when a next action needs analysis
depthNoProgressive exploration depth for explore mode
focusNoOptional component/file/symbol focus for explore mode
queryNoKeyword query for diagnose_issue
intentNoOptional natural intent alias; when present it is treated like mode
symbolNoTarget symbol for before_edit, delete_code, explain_symbol, or impact flows
targetNoWorkspace impact target for cross_project_impact
compactNo
executeNoWhen true, execute non-recursive nextActions and return completedActions, failedActions, evidence, and answerSummary
symptomNoBug symptom or user report for diagnose_issue
languageNoauto
questionNoNatural-language question for ask mode
errorTextNoObserved error text/log excerpt for diagnose_issue
changedPathNoKnown changed or suspicious file path for diagnose_issue
changedSymbolsNoChanged symbol names for after_edit flows

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.17.0-beta.3
    • changedInput schema / properties / language / enum
      Previous value: -[
-  "rust",
-  "cangjie",
-  "arkts",
-  "typescript",
-  "javascript",
-  "c",
-  "cpp",
-  "python",
-  "shell",
-  "auto"
-]New value: +[
+  "rust",
+  "cangjie",
+  "arkts",
+  "typescript",
+  "javascript",
+  "c",
+  "cpp",
+  "python",
+  "shell",
+  "objc",
+  "auto"
+]
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

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

The annotations already declare the tool read-only, idempotent, non-destructive, and closed-world, so the description need not repeat safety basics. The description adds useful orchestration context, but does not explain what the execute flag does, how delete_code behaves, or what returning completedActions and failedActions implies.

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?

The description is two tight sentences with no filler, front-loading the tool's role and following with actionable routing guidance. Every clause supports selection or invocation.

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 17-parameter orchestration tool with many modes and no output schema, the description is only minimum viable: it covers a few key modes but not the full mode set, the execute behavior, or what a caller gets back in different flows. The rich schema and annotations fill much of the gap, but the description itself is incomplete relative to the tool's complexity.

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 high at 88%, so the schema itself documents most parameters. The description restates the purpose of a few mode values (ask, explore, diagnose_issue, before_edit) but adds little meaning beyond the schema and omits many other modes and the execute parameter.

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?

The description identifies the tool as an 'AI intent router and orchestration layer' and positions it as the first entry point when unsure which CodeLattice tool or root to call. This is clear but somewhat abstract; it does not state a concrete verb+resource as precisely as a high-scoring definition would, though the mode examples help.

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?

It explicitly says to use this tool FIRST when unsure and maps key modes to usage scenarios: ask for natural-language routing, explore for orientation, diagnose_issue for symptoms, and before_edit only after a concrete target is known. This gives clear when-to-use guidance and sequencing constraints.

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