Skip to main content
Glama

Test an on-prem handler on the user's runner

test_runner_handler

Run a SignalR (on-prem) block's C# handler with sample input on a runner started with --test, return its output, and iterate before baking the handler into a download.

Instructions

Pushes a SignalR (on-prem) block's C# handler + sample input to the user's runner — which must be running in TEST MODE (dotnet run -- --test) — and returns its output. The on-prem twin of test_block: use it to iterate on a handler before the user bakes it into a download. signalRBlockId is the block's guid (the signalRGuid from get_workspace_content). Omit handlerCode to run the saved handler. Times out if the runner isn't in test mode — if so, tell the user to start it with --test.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "signalRBlockId": "<signalRBlockId>"
    },
    "name": "test_runner_handler"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputNoSample value the handler reads as `input`.
handlerCodeNoC# handler to test now. Omit to run the block's saved handler.
signalRBlockIdYesThe SignalR block's guid (its signalRGuid).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does most of it: it discloses the hard precondition (the runner must be started with `dotnet run -- --test`), the timeout failure mode, and the corrective instruction to give the user. The only gap is that 'returns its output' does not characterize the response payload, and there is no output schema to fall back on.

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 dense sentences, front-loaded with the action and precondition, then the sibling differentiation, then the failure remedy. No filler or restatement of the name/title.

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 three-parameter tool with no output schema, the definition covers the precondition, the parameter provenance, and the common failure path an agent must recover from. What remains thin is the return value, which is described only as 'its output' – acceptable but not fully informative for a tool whose whole purpose is producing that output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning beyond the schema: signalRBlockId is identified as the block's guid traceable to the signalRGuid from get_workspace_content, and the handlerCode omit-behavior is restated as a functional rule rather than a type note. The `input` parameter is left to the schema's own 'sample value the handler reads as input' description.

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: pushes a SignalR block's C# handler plus sample input to the user's runner and returns its output. It explicitly positions itself as the on-prem twin of test_block, so an agent can distinguish the two without opening either schema.

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

Usage Guidelines5/5

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

Gives an explicit use case (iterate on a handler before the user bakes it into a download), names the alternative (test_block) as the non-on-prem counterpart, and adds an invocation branch: omit handlerCode to run the saved handler. It also tells the agent what to do when the call times out.

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