Skip to main content
Glama

Secure Autonomous Register

Search cases

search_cases
Read-onlyIdempotent

Find Register cases by keywords (company, system, failure, e.g. 'coding agent deletes database', 'robotaxi', 'prompt injection email'), optionally filtered by world (physical, bridge, software, transaction, boundary) or by a control ID that was missing or failed. Returns short summaries with URLs.

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
limitNoHow many results to return, from 1 to 50. Default 10.
queryNoKeywords to match: a company, a system or a kind of failure, such as 'coding agent deletes database' or 'robotaxi'. A case must match at least one word. Leave out to list cases by the other filters alone.
worldNoKeep only cases in one world: physical (machines such as vehicles and robots), bridge (software acting on machines), software (software agents), transaction (agents moving money) or boundary (a machine case at the edge of the Register's scope). Leave out for all worlds.
controlNoKeep only cases where this control failed or was absent. A control ID such as C-E3; list_controls gives every ID.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / control / description
      Previous value: -"Control ID such as C-E3"New value: +"Keep only cases where this control failed or was absent. A control ID such as C-E3; list_controls gives every ID."
    • addedInput schema / properties / limit / description
      Added value: +"How many results to return, from 1 to 50. Default 10."
    • addedInput schema / properties / query / description
      Added value: +"Keywords to match: a company, a system or a kind of failure, such as 'coding agent deletes database' or 'robotaxi'. A case must match at least one word. Leave out to list cases by the other filters alone."
    • addedInput schema / properties / world / description
      Added value: +"Keep only cases in one world: physical (machines such as vehicles and robots), bridge (software acting on machines), software (software agents), transaction (agents moving money) or boundary (a machine case at the edge of the Register's scope). Leave out for all worlds."
    • addedInput schema / properties / world / enum
      Added value: +[
      +  "physical",
      +  "bridge",
      +  "software",
      +  "transaction",
      +  "boundary"
      +]
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile needs no restating. The description adds genuine behavioral context beyond that: results are short summaries, not full cases, and each carries a URL. It does not discuss match ranking or result ordering, which keeps it from 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded and efficient: purpose, filters, then return shape in two sentences with no filler. The parenthetical keyword examples duplicate the schema's own examples, costing a little space without adding new 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?

Four optional parameters, no output schema, and a read-only search — the description covers what is searched, how to narrow it, and what comes back, which is enough to call it correctly. Ordering and whether summaries are truncated are the only unresolved details.

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 coverage is 100% and the schema already documents every parameter, including the limit bounds, the world enum meanings, and the control-ID format. The description's keyword examples ('coding agent deletes database', 'robotaxi', 'prompt injection email') and world list largely restate schema content, so it adds meaning only marginally beyond structured fields.

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?

States a specific verb and resource ('Find Register cases by keywords') plus the two optional filter axes (world, control ID) and the return format ('short summaries with URLs'). It also implicitly separates itself from get_case by framing itself as keyword retrieval rather than ID lookup, and names list_controls as the source of control IDs.

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?

Explains the query-omitted mode ('Leave out to list cases by the other filters alone') and points to list_controls for obtaining valid control IDs, which is real when-to-use guidance. It stops short of explicitly routing the agent to get_case for full case detail or recent_signals for freshness, so it is clear context rather than 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