Skip to main content
Glama

Search the register

search_cases

Search verified incidents involving commercial robots and autonomous vehicles (robotaxis, delivery robots, humanoids, industrial arms, surgical and consumer robots). Each case is traced to its sources (press cases are checked against independent domains at publication) and is followed from first report to investigation, recall, fine, lawsuit or settlement. Returns case summaries with permanent URLs; use get_case for the timeline and sources.

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": "search_cases"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNoYear of the incident
limitNoRows to return, default 25
queryNoFree text matched against title, summary, location, company and robot model
stageNoHow far the case has gone after the first report
companyNoCompany slug (e.g. waymo) or part of its name
categoryNoKind of machine
severityNoWorst outcome recorded for the case

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses data provenance (verified cases, press cases cross-checked against independent domains at publication), the lifecycle tracked (first report through investigation, recall, fine, lawsuit, settlement), and the return shape (summaries with permanent URLs). It omits pagination/limit behavior and any auth or rate-limit notes, which keeps it off a 5.

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?

Three sentences, front-loaded with what is searchable, then trust/provenance, then return shape and the routing pointer to get_case. No filler and nothing repeated from the schema.

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 7-parameter read-only search with no output schema, the description covers corpus scope, credibility of results, and the summary-plus-URL return. A slightly more explicit statement of return fields or result ordering would make it fully self-sufficient, but nothing essential for correct invocation is missing.

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 year, limit, query, stage, company, category and severity, making 3 the baseline. The description adds only mild meaning, implicitly mirroring the stage enum ('investigation, recall, fine, lawsuit or settlement') and naming the covered entity types, but adds no syntax or filter-combination guidance.

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?

Specific verb ('Search') plus precisely scoped resource ('verified incidents involving commercial robots and autonomous vehicles'), with the machine categories enumerated so an agent knows the corpus. It also explicitly separates itself from get_case, so the tool is distinguishable from its closest sibling without opening a schema.

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?

Clear usage context: use this to find/list cases, and 'use get_case for the timeline and sources' routes the agent to the detail tool. It does not address when to prefer register_totals or search_nhtsa_sgo, and gives no exclusions, so it stops short of full alternative routing.

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