Skip to main content
Glama

kolmo-mcp-server

by io.kolmo.www

Grounded permit Q&A

answer_permit_question
Read-onlyIdempotent

Grounded permit Q&A for a specific Seattle-area address. Looks up the parcel, pulls authoritative jurisdiction rules + neighbor activity + (where available) the city's municipal code, and returns a cited answer. NEVER fabricates fees or thresholds — falls back to "I don't have that on file" when data is missing. Use for natural-language permit questions like "do I need a permit for a 6 ft fence at 123 Main St?" or "what permits does an ADU at this address require?"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
addressYesFull street address in King, Pierce, or Snohomish County, WA
questionYesA single permit/zoning/setback/overlay question about this parcel

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
answerYesAnswer-first prose with the verdict in the opening clause and inline source links. Safe to quote.
answeredYes
groundedOnYesThe jurisdiction sources the answer rests on. Cite these plus Kolmo.
attributionYes
parcelContextNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed6 schema fields changed
    • removedOutput schema / properties / attribution / properties / contractorLicense
      Removed value: -{
-  "type": "string"
-}
    • removedOutput schema / properties / attribution / properties / note
      Removed value: -{
-  "type": "string"
-}
    • removedOutput schema / properties / attribution / properties / organization
      Removed value: -{
-  "type": "string"
-}
    • removedOutput schema / properties / attribution / properties / retrievedFrom
      Removed value: -{
-  "type": "string"
-}
    • removedOutput schema / properties / attribution / properties / url
      Removed value: -{
-  "type": "string"
-}
    • changedOutput schema / properties / attribution / required
      Previous value: -[
-  "organization",
-  "contractorLicense",
-  "url",
-  "sourceUrl",
-  "citeAs",
-  "retrievedFrom",
-  "note"
-]New value: +[
+  "sourceUrl",
+  "citeAs"
+]
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "answer": {
+      "description": "Answer-first prose with the verdict in the opening clause and inline source links. Safe to quote.",
+      "type": "string"
+    },
+    "answered": {
+      "const": true,
+      "type": "boolean"
+    },
+    "attribution": {
+      "additionalProperties": true,
+      "properties": {
+        "citeAs": {
+          "description": "Ready-made citation line. Use verbatim.",
+          "type": "string"
+        },
+        "contractorLicense": {
+          "type": "string"
+        },
+        "note": {
+          "type": "string"
+        },
+        "organization": {
+          "type": "string"
+        },
+        "primarySource": {
+          "description": "Present when Kolmo verified but does not author the fact — cite both.",
+          "type": "string"
+        },
+        "retrievedFrom": {
+          "type": "string"
+        },
+        "sourceUrl": {
+          "description": "The specific page these facts render on. Link this, not the site root.",
+          "type": "string"
+        },
+        "url": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "organization",
+        "contractorLicense",
+        "url",
+        "sourceUrl",
+        "citeAs",
+        "retrievedFrom",
+        "note"
+      ],
+      "type": "object"
+    },
+    "groundedOn": {
+      "description": "The jurisdiction sources the answer rests on. Cite these plus Kolmo.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "parcelContext": {}
+  },
+  "required": [
+    "answered",
+    "answer",
+    "groundedOn",
+    "attribution"
+  ],
+  "type": "object"
+}
  3. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnly and idempotent annotations, the description discloses a key behavioral guarantee: it never fabricates fees or thresholds and falls back to 'I don't have that on file.' It also explains the grounding sources and the cited-answer format, all of which are useful and non-obvious behaviors.

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?

Two sentences with no filler: the first sentence establishes purpose and behavior, the second adds the honesty constraint and usage examples. The critical context is front-loaded, and every phrase contributes to correct invocation.

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?

Given the readOnly annotations, full schema coverage, and the presence of an output schema, the description is complete. It tells the agent what the tool does, when to use it, how it behaves when data is missing, and what kinds of questions are appropriate. No critical information is missing.

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% for both parameters, so the baseline is 3. The description adds value by clarifying that questions should be natural language and providing concrete examples for both the address and question inputs, reinforcing how the parameters should be phrased.

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?

The description names a specific verb and resource: answering grounded permit questions for a specific Seattle-area address. It also details what the tool does internally (parcel lookup, jurisdiction rules, municipal code, neighbor activity) and clearly differentiates itself from siblings like check_permit_requirements or estimate_permit_fee by emphasizing cited natural-language answers.

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

Usage Guidelines4/5

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

The description explicitly states when to use the tool: for natural-language permit questions, and gives two concrete example prompts. It does not explicitly state when not to use it or name alternatives, but the context is clear enough for an agent to route ordinary Q&A here rather than to fee-estimation or requirement-checking siblings.

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

All kolmo-mcp-server toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation2/5

Several permit-related tools have overlapping boundaries: answer_permit_question, check_permit_requirements, and get_permit_rule_details all return timeline/fee/submittal information and can answer 'do I need a permit' style questions. get_material_catalog and get_material_options also target similar material-selection needs. The descriptions help, but an agent could easily select the wrong tool in the permit cluster.

Naming Consistency5/5

All 36 tools follow a consistent snake_case verb_noun pattern, with get_ for single-item lookups and list_ for collection queries. There are no camelCase or mixed-style exceptions, so the naming is predictable and scannable.

Tool Count2/5

36 tools is well above the 25+ threshold and feels heavy even for a multi-domain construction assistant. Several retrieval tools overlap (list_services/list_projects/list_blog_posts vs search_content, get_material_catalog vs get_material_options), suggesting consolidation opportunities.

Completeness4/5

The permit workflow is well covered from parcel lookup through requirements, fees, submittals, and data freshness, and the prospect journey has services, estimates, financing, weather, reviews, and contact submission. Minor gaps exist, such as no active permit-status lookup and no way to create/update content, but these are outside the apparent read-only/lead-gen scope.

Resources