Skip to main content
Glama

Food Compliance Agency — R638 COA & Hygiene Audits

Request Compliance Audit

request_compliance_audit

Submits an on-site Certificate of Acceptability (CoA) pre-audit or municipal licensing inquiry directly to the Food Compliance Agency consulting desk. When to use: Call this tool when you specifically need to execute 'request_compliance_audit' on Food Compliance Agency (foodcompliance.co.za). Do NOT use this tool when another specialized tool fits better (use 'check_coa_requirements' or 'get_municipal_health_guidelines' or 'get_food_handler_training_standards' for their respective operations). Parameters: business_name (required), contact_person (required), email (optional), phone (required), premises_type (required), location_city (required), urgent (optional). Behavior & Side Effects: Creates a live record/session in the backend database; no authentication required for public initiation; rate-limited to 60 requests/min per IP. Returns: Structured JSON object containing status, matched records or computed metrics, and canonical action URLs.

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": {
      "business_name": "<business_name>",
      "contact_person": "<contact_person>",
      "phone": "<phone>",
      "premises_type": "<premises_type>",
      "location_city": "<location_city>"
    },
    "name": "request_compliance_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailNoParameter 'email' (string). [Optional: omit to use server default filter].
phoneYesParameter 'phone' (string). [Required: non-empty valid value must be supplied].
urgentNoParameter 'urgent' (boolean). [Optional: omit to use server default filter].
business_nameYesParameter 'business_name' (string). [Required: non-empty valid value must be supplied].
location_cityYesParameter 'location_city' (string). [Required: non-empty valid value must be supplied].
premises_typeYesParameter 'premises_type' (string). [Required: non-empty valid value must be supplied].
contact_personYesParameter 'contact_person' (string). [Required: non-empty valid value must be supplied].

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / business_name / description
      Added value: +"Parameter 'business_name' (string). [Required: non-empty valid value must be supplied]."
    • addedInput schema / properties / contact_person / description
      Added value: +"Parameter 'contact_person' (string). [Required: non-empty valid value must be supplied]."
    • addedInput schema / properties / email / description
      Added value: +"Parameter 'email' (string). [Optional: omit to use server default filter]."
    • addedInput schema / properties / location_city / description
      Added value: +"Parameter 'location_city' (string). [Required: non-empty valid value must be supplied]."
    • addedInput schema / properties / phone / description
      Added value: +"Parameter 'phone' (string). [Required: non-empty valid value must be supplied]."
    • addedInput schema / properties / premises_type / description
      Added value: +"Parameter 'premises_type' (string). [Required: non-empty valid value must be supplied]."
    • addedInput schema / properties / urgent / description
      Added value: +"Parameter 'urgent' (boolean). [Optional: omit to use server default filter]."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false/openWorld=true/idempotentHint=false, but the description adds real operational context: it writes a live backend record, requires no authentication for public initiation, and is rate-limited at 60 requests/min per IP. What is missing is whether repeat submissions create duplicates (relevant given non-idempotent) and any eligibility constraint on which premises qualify.

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

Conciseness3/5

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

The labeled sections (When to use / Do NOT / Parameters / Behavior & Side Effects / Returns) are well front-loaded. But the parameter enumeration is pure duplication of the schema, and the 'Call this tool when you specifically need to execute request_compliance_audit' sentence is tautological filler that earns no place.

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?

For a non-idempotent open-world submission tool with no output schema, the description covers side effects, auth, limits, and a return shape, which is enough to invoke it correctly. The return clause ('status, matched records or computed metrics') reads like a generic template and is slightly ill-fitting for a submission action, leaving the confirmation semantics a bit vague.

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 all seven parameters and their required/optional status. The description's parameter list restates that plus the required/optional flags without adding format or validation semantics (e.g. what values premises_type or location_city accept). Baseline 3 applies when the schema does the heavy lifting.

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 first sentence names a specific verb (submits) and resource (CoA pre-audit / municipal licensing inquiry to the Food Compliance Agency consulting desk), which is far more informative than the title. However, the follow-on 'When to use: Call this tool when you specifically need to execute request_compliance_audit' is circular and dilutes rather than sharpens the distinction from siblings.

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?

It explicitly names three alternatives ('check_coa_requirements', 'get_municipal_health_guidelines', 'get_food_handler_training_standards') and tells the agent not to use this tool when one of them fits. The guidance is weakened by 'for their respective operations', which leaves the actual boundary condition to inference instead of stating e.g. 'use check_coa_requirements to learn which documents you need before submitting'.

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.

Resources