> ## Documentation Index
> Fetch the complete documentation index at: https://resq-dependabot-github-actions-github-actions-478e18be3d.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Tools
# resq\_mcp.hce.tools
MCP tool wrappers for HCE domain.
## logging
## time
## UTC
## datetime
## FastMCPError
## IncidentValidation
## MissionParameters
## MAX\_INCIDENTS
## MAX\_MISSIONS
## incidents
## mcp
## missions
#### logger
#### validate\_incident
```python theme={null}
@mcp.tool()
async def validate_incident(val: IncidentValidation) -> str
```
Submit validation result for an incident report.
Used by human operators or automated validation systems (HCE) to
confirm or reject incident reports before triggering full response.
**Arguments**:
* `val` - IncidentValidation with:
* incident\_id: ID of incident being validated
* is\_confirmed: True=confirmed, False=rejected/false positive
* validation\_source: Who/what validated (e.g., "Human-Operator")
* correlated\_pre\_alert\_id: Optional linked PDIE alert
* notes: Validation reasoning and evidence
**Returns**:
* `str` - Confirmation message indicating action taken:
"Incident \{id} successfully CONFIRMED." or
"Incident \{id} successfully REJECTED."
**Example**:
> > > from resq\_mcp.hce.models import IncidentValidation
> > > validation = IncidentValidation(
> > > ... incident\_id="INC-123",
> > > ... is\_confirmed=True,
> > > ... validation\_source="Human-Operator-Alice",
> > > ... notes="Confirmed via video evidence and ground reports"
> > > ... )
> > > result = await validate\_incident(validation)
> > > print(result) # "Incident INC-123 successfully CONFIRMED."
Workflow:
1. Edge AI detects incident (low confidence)
2. HCE cross-references with PDIE/sensors
3. If ambiguous -> human review required
4. Operator submits validation via this tool
5. If confirmed -> trigger response strategy
6. If rejected -> log as false positive, update ML model
Audit Trail:
All validations logged with timestamp, source, and reasoning
for post-incident analysis and ML model refinement.
#### update\_mission\_params
```python theme={null}
@mcp.tool()
async def update_mission_params(drone_id: str,
strategy_id: str,
is_urgent: bool = False) -> MissionParameters
```
Push authorized mission parameters to a drone for an approved strategy.
Completes the deployment workflow after a strategy has been approved:
get\_deployment\_strategy -> (human approval) -> update\_mission\_params -> drone executes.
**Arguments**:
* `drone_id` - Target drone identifier (e.g., "DRONE-Alpha").
* `strategy_id` - Approved strategy ID from get\_deployment\_strategy (e.g., "STRAT-X1Y2Z3").
* `is_urgent` - If True, sets risk\_tolerance=0.9 (aggressive routing) instead of the
default 0.5. Must be explicitly set — urgency is never derived from the
strategy\_id string to prevent injection attacks.
**Returns**:
* `MissionParameters` - Authorized parameter set including mission ID, allowed actions,
risk tolerance, and a deterministic blockchain-anchored strategy hash.
**Raises**:
* `FastMCPError` - If the drone already has an active mission for a different strategy
(conflict guard), or if the mission store is at capacity.
**Example**:
> > > params = await update\_mission\_params("DRONE-Alpha", "STRAT-ABCD1234", is\_urgent=True)
> > > print(params.authorized\_actions)
> > > print(params.strategy\_hash) # 0xSHA256(strategy\_id:mission\_id)