CrimeMetric

Incident counts

incident_stats

Read-only

Counts of police-published records around a point by type and record type, by month, and against the same-length period before, with the sources behind them. Counts describe published records, not all crime.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "incident_stats"
  }
}

Input Schema

Name	Required	Description
`to`	No	Last day, YYYY-MM-DD (default: today)
`lat`	No	Latitude
`lon`	No	Longitude
`from`	No	First day, YYYY-MM-DD (default: 90 days before `to`)
`crime`	No	Only these types: murder, rape, robbery, aggravated_assault, burglary, shoplifting, theft_from_vehicle, other_larceny, motor_vehicle_theft, simple_assault, intimidation, vandalism, weapons, drugs_alcohol, disorderly_conduct, trespass, theft_unspecified, assault_unspecified, other_offense, or a call_* type
`address`	No	A U.S. street address
`radius_m`	No	Radius in meters (default 500; plan caps apply)
`record_type`	No	offense, report, cfs (calls for service), unknown. Default leaves out cfs.
`include_calls`	No	Include calls for service and records that read as calls (alarms, traffic, welfare checks). Default false, unless crime names a call type or record_type includes cfs.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 11, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description goes further by disclosing data provenance ('with the sources behind them') and the crucial semantic limit that counts reflect published records rather than all crime. The prior-period comparison behavior is also stated, which is not derivable from annotations. This is meaningful added context rather than restatement.

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, front-loaded with the core aggregation capability and closed with the one caveat an agent must know. The compressed clause structure ('by type and record type, by month, and against the same-length period before') is dense but every element carries information.

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 nine-parameter, zero-required aggregation tool with no output schema, the description adequately conveys what comes back: counts broken out by type, by record type, by month, plus a prior-period comparison and sources. The mechanics of specifying the point and time window live in the schema. Only the routing relationship to sibling count/index tools is left unaddressed.

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 explains lat/lon, address, from/to defaults, radius caps, crime types, record_type and include_calls. The description adds only framing about what the resulting counts represent, not per-parameter meaning. Baseline 3 is appropriate when the schema carries the parameter burden.

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 description states a specific verb (counts) and resource (police-published records) plus the aggregation axes: by type, by record type, by month, and against the prior same-length period. That is far more informative than the title 'Incident counts'. It stops short of naming a sibling like nearby_incidents, so the distinction from listing tools must be inferred.

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?

There is no explicit when-to-use or when-not-to-use statement and no alternative tool is named, even though crime_index, nearby_incidents and crime_index_batch are plausible neighbors. The clinical caveat 'Counts describe published records, not all crime' aids interpretation but is not routing guidance. Usage is only implied by the description of the aggregation output.

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

All CrimeMetric tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?