Skip to main content
Glama
geneontology

Noctua MCP Server

Official
by geneontology

add_evidence_to_fact

Add experimental evidence and source references to facts in GO-CAM models to support biological assertions with documented proof.

Instructions

Add evidence to an existing fact in a GO-CAM model.

Args: model_id: The GO-CAM model identifier subject_id: Subject of the fact object_id: Object of the fact predicate_id: Predicate of the fact eco_id: Evidence code (e.g., "ECO:0000353") sources: List of source references (e.g., ["PMID:12345"]) with_from: Optional list of with/from references

Returns: Barista API response

Examples: # Add experimental evidence from a paper add_evidence_to_fact( "gomodel:12345", "mf1", "gp1", "RO:0002333", "ECO:0000353", # physical interaction evidence ["PMID:12345678"] )

# Add multiple sources
add_evidence_to_fact(
    "gomodel:12345", "mf1", "gp1", "RO:0002333",
    "ECO:0000314",  # direct assay evidence
    ["PMID:12345678", "PMID:87654321", "doi:10.1234/example"]
)

# Add evidence with with/from (e.g., for IPI)
add_evidence_to_fact(
    "gomodel:12345", "mf1", "gp1", "RO:0002333",
    "ECO:0000353",  # IPI
    ["PMID:12345678"],  
    ["UniProtKB:Q9Y6K9", "UniProtKB:P38398"]  # interacting partners
)

# Common evidence codes:
# ECO:0000314 - direct assay evidence
# ECO:0000353 - physical interaction evidence (IPI)
# ECO:0000315 - mutant phenotype evidence (IMP)
# ECO:0000316 - genetic interaction evidence (IGI)
# ECO:0000318 - biological aspect of ancestor evidence (IBA)
# ECO:0000269 - experimental evidence

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
model_idYes
subject_idYes
object_idYes
predicate_idYes
eco_idYes
sourcesYes
with_fromNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The primary handler implementation for the MCP tool 'add_evidence_to_fact'. This async function is decorated with @mcp.tool(), defining its schema via type hints and docstring. It delegates to BaristaClient.req_add_evidence_to_fact, executes the batch, and handles validation/errors with detailed responses.
    @mcp.tool()
    async def add_evidence_to_fact(
        model_id: str,
        subject_id: str,
        object_id: str,
        predicate_id: str,
        eco_id: str,
        sources: List[str],
        with_from: Optional[List[str]] = None
    ) -> Dict[str, Any]:
        """
        Add evidence to an existing fact in a GO-CAM model.
    
        Args:
            model_id: The GO-CAM model identifier
            subject_id: Subject of the fact
            object_id: Object of the fact
            predicate_id: Predicate of the fact
            eco_id: Evidence code (e.g., "ECO:0000353")
            sources: List of source references (e.g., ["PMID:12345"])
            with_from: Optional list of with/from references
    
        Returns:
            Barista API response
    
        Examples:
            # Add experimental evidence from a paper
            add_evidence_to_fact(
                "gomodel:12345", "mf1", "gp1", "RO:0002333",
                "ECO:0000353",  # physical interaction evidence
                ["PMID:12345678"]
            )
    
            # Add multiple sources
            add_evidence_to_fact(
                "gomodel:12345", "mf1", "gp1", "RO:0002333",
                "ECO:0000314",  # direct assay evidence
                ["PMID:12345678", "PMID:87654321", "doi:10.1234/example"]
            )
    
            # Add evidence with with/from (e.g., for IPI)
            add_evidence_to_fact(
                "gomodel:12345", "mf1", "gp1", "RO:0002333",
                "ECO:0000353",  # IPI
                ["PMID:12345678"],  
                ["UniProtKB:Q9Y6K9", "UniProtKB:P38398"]  # interacting partners
            )
    
            # Common evidence codes:
            # ECO:0000314 - direct assay evidence
            # ECO:0000353 - physical interaction evidence (IPI)
            # ECO:0000315 - mutant phenotype evidence (IMP)
            # ECO:0000316 - genetic interaction evidence (IGI)
            # ECO:0000318 - biological aspect of ancestor evidence (IBA)
            # ECO:0000269 - experimental evidence
        """
        client = get_client()
        reqs = client.req_add_evidence_to_fact(
            model_id, subject_id, object_id, predicate_id,
            eco_id, sources, with_from
        )
        resp = client.m3_batch(reqs)
    
        if resp.validation_failed:
            return {
                "success": False,
                "error": "Validation failed",
                "reason": resp.validation_reason,
                "rolled_back": True,
                "fact": {
                    "subject": subject_id,
                    "predicate": predicate_id,
                    "object": object_id
                },
                "evidence": {
                    "eco_id": eco_id,
                    "sources": sources,
                    "with_from": with_from
                }
            }
    
        if resp.error:
            return {
                "success": False,
                "error": resp.error,
                "model_id": model_id,
                "fact": {
                    "subject": subject_id,
                    "predicate": predicate_id,
                    "object": object_id
                }
            }
    
        # Return minimal success response
        return {
            "success": True,
            "evidence_added": True,
            "eco_id": eco_id
        }
  • The @mcp.tool() decorator registers this function as an MCP tool named 'add_evidence_to_fact' in the FastMCP instance.
    @mcp.tool()
  • Input schema defined by function parameters with type annotations: model_id (str), subject_id (str), object_id (str), predicate_id (str), eco_id (str), sources (List[str]), with_from (Optional[List[str]]). Returns Dict[str, Any]. Detailed examples in docstring.
    async def add_evidence_to_fact(
        model_id: str,
        subject_id: str,
        object_id: str,
        predicate_id: str,
        eco_id: str,
        sources: List[str],
        with_from: Optional[List[str]] = None
    ) -> Dict[str, Any]:
Behavior3/5

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

With no annotations provided, the description carries full burden. It implies a write operation ('Add evidence') but doesn't disclose behavioral traits like required permissions, whether the operation is idempotent, rate limits, or error conditions. The examples add some context but lack explicit behavioral disclosure.

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 appropriately front-loaded with a clear purpose statement, but the extensive examples and evidence code list (while helpful) make it lengthy. Some sentences in the examples could be condensed, though the structure is logical with purpose, args, returns, and examples.

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?

Given 7 parameters with 0% schema coverage and no annotations, the description does well by explaining all parameters and providing examples. However, it lacks behavioral context (e.g., permissions, errors) and doesn't clarify the output beyond 'Barista API response', though an output schema exists to compensate.

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?

Schema description coverage is 0%, so the description must fully compensate. It provides detailed semantic explanations for all 7 parameters (e.g., 'eco_id: Evidence code', 'sources: List of source references'), includes examples with concrete values, and lists common evidence codes, adding significant meaning beyond the bare schema.

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 clearly states the specific action ('Add evidence') and target resource ('to an existing fact in a GO-CAM model'), distinguishing it from sibling tools like 'add_fact' or 'remove_fact'. The verb+resource combination is precise and unambiguous.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'add_fact' or 'remove_fact', nor does it mention prerequisites (e.g., the fact must already exist). The examples show usage but don't explicitly state context or exclusions.

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/geneontology/noctua-mcp'

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