Skip to main content
Glama

list_substances_by_class_and_safety

Filter substances from the EFSA OpenFoodTox database by classification and safety criteria to identify food additives, pesticides, or contaminants with specific mutagenicity, genotoxicity, or carcinogenicity assessments for regulatory compliance and safety analysis.

Instructions

Retrieves substances from the EFSA OpenFoodTox database filtered by safety assessment
criteria (mutagenicity, genotoxicity, carcinogenicity) and substance classification.
This tool enables discovery of substances based on their safety profile and regulatory
category, useful for comparative safety analysis and regulatory compliance queries.

## Example questions it can answer:
### Classification + Safety Status Queries
By category:
* "What food additives are genotoxic?"
* "List pesticides that are carcinogenic"
* "Show me flavourings that are mutagenic"
* "What sensory additives have positive genotoxicity results?"
### Safety screening:
"Which substances are both mutagenic and genotoxic?"
* "Find substances that are positive for carcinogenicity"
* "What additives have ambiguous safety data?"
* "List substances with no mutagenicity data"
### Combined filters:
* "What food additives are not genotoxic?" (Negative)
* "Show pesticides that are not carcinogenic"
* "List flavourings with ambiguous genotoxicity results"
### Regulatory & Compliance Queries
"Which food additives have positive mutagenicity assessments?"
* "What pesticides are flagged as genotoxic?"
* "List substances in the 'Food additives' category with safety concerns"
* "Show me technological additives that are not mutagenic"
### Research & Analysis Queries
* "What substances have 'reproductive' in their study remarks?"
* "Find additives with 'chronic' mentioned in remarks"
* "List substances with 'developmental' toxicity in remarks"
* "Show me substances where remarks contain 'neurotoxicity'"
### Comparative Safety Queries
* "Compare all food additives by their genotoxicity status"
* "Which category has the most substances with positive carcinogenicity?"
"List all substances with positive results in any safety category"
### Data Quality Queries
* "What substances have 'No data' for mutagenicity?"
* "Show me substances with 'Not determined' safety assessments"
* "List additives with incomplete safety data"

Args:
    sub_class: Optional SUB_OP_CLASS filter. Accepts partial matches (case-insensitive LIKE).
               Examples:
               - "additives" matches "Food additives", "Nutritional additives", "Sensory additives", etc.
               - "food" matches "Food additives", "Food contact materials"
               - "pesticides" matches "Pesticides"
               - "Food additives" (exact match also works)
               Valid full values (all possible SUB_OP_CLASS values):
               - "No category"
               - "Cocciodiostats/Hormones/Histomonostats"
               - "Persistent organic pollutants"
               - "Natural plant product contaminants"
               - "Mycotoxins"
               - "Melamine"
               - "Processing contaminants"
               - "Marine biotoxins"
               - "Heavy metal ions and metalloids"
               - "Nutritional additives"
               - "Sensory additives"
               - "Technological additives"
               - "Zootechnical additives"
               - "Feed intended for particular nutritional purposes"
               - "Food additives"
               - "Food contact materials"
               - "Processing aids"
               - "Nutrient sources"
               - "Pesticides"
               - "Flavourings"
    is_mutagenic: Optional IS_MUTAGENIC filter (exact match: "Positive", "Negative", "Ambiguous", etc.)
    is_genotoxic: Optional IS_GENOTOXIC filter (exact match: "Positive", "Negative", "Ambiguous", etc.)
    is_carcinogenic: Optional IS_CARCINOGENIC filter (exact match: "Positive", "Negative", "Ambiguous", etc.)
    remarks_contains: Optional text search in REMARKS_STUDY (case-insensitive LIKE, substring match)
    limit: Maximum number of results to return (default: 10)

Returns:
    JSON string containing a DataFrame with substance records. Each record includes
    substance identification, classification, and alternative names/E-numbers.
    The function also returns a total_count indicating how many substances match
    the criteria before the limit is applied.

The returned data includes:
- Substance identification: SUB_COM_ID (unique identifier)
- Chemical details: COM_NAME (chemical name), COM_TYPE (single/mixture/botanical/synthetic)
- Classification: SUB_TYPE (substance type qualifier)
- Alternative names: DESCRIPTION (comma-separated synonyms, E-numbers, trade names)

Joins: STUDY → COMPONENT (by SUB_COM_ID) → SYNONYM (by SUB_COM_ID)
Returns unique substances (DISTINCT by SUB_COM_ID).

Note: Multiple synonyms per substance are aggregated into a comma-separated list.
Use the search_substance tool to get detailed information about specific substances
from the results.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sub_classNo
is_mutagenicNo
is_genotoxicNo
is_carcinogenicNo
remarks_containsNo
limitNo
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it's a read-only retrieval tool (implied by 'retrieves'), specifies data source (EFSA OpenFoodTox database), explains result format (JSON string with DataFrame), includes pagination behavior via 'limit' parameter, describes data joins and uniqueness (DISTINCT by SUB_COM_ID), and mentions aggregation of synonyms. However, it doesn't cover potential rate limits, authentication requirements, or error conditions.

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 description is well-structured with clear sections (purpose, examples, parameters, returns, notes) but is excessively long due to the extensive example questions list. While the examples are helpful, they occupy disproportionate space, making the description verbose. The core information is front-loaded, but the length reduces overall conciseness.

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 tool's complexity (6 parameters, no annotations, no output schema), the description provides exceptional completeness. It covers purpose, usage scenarios, detailed parameter semantics, return format, data structure, joins, uniqueness constraints, aggregation behavior, and when to use alternative tools. For a filtering/retrieval tool with rich functionality, this description leaves no significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description fully compensates by providing comprehensive parameter documentation. Each parameter gets detailed explanations: 'sub_class' includes partial matching behavior, examples, and complete valid value list; safety filters specify exact match requirements and enum values; 'remarks_contains' describes substring matching; 'limit' explains default behavior. This adds substantial value beyond what the bare schema provides.

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 explicitly states the tool 'retrieves substances from the EFSA OpenFoodTox database filtered by safety assessment criteria and substance classification.' It specifies the exact resource (EFSA OpenFoodTox database), filtering criteria (mutagenicity, genotoxicity, carcinogenicity, classification), and distinguishes it from sibling tools like 'search_substance' by focusing on filtered discovery rather than detailed information retrieval.

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?

The description provides extensive usage guidance with a dedicated 'Example questions it can answer' section, covering classification+safety queries, safety screening, combined filters, regulatory compliance, research analysis, comparative safety, and data quality queries. It explicitly mentions when to use an alternative tool ('Use the search_substance tool to get detailed information about specific substances from the results'), making it clear when this tool is appropriate versus siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/spyrosze/mcp-openfoodtox'

If you have feedback or need assistance with the MCP directory API, please join our Discord server