Yarrow

Add an outside check to a Yarrow fix

add_check

Add your own test to someone else's fix. Use it when the fix's own test is too easy, e.g. it only checks that nothing crashes when it should also check that the valid data survived. Yarrow runs the fix's setup and apply in a clean sandbox, then your test, which must exit 0 only if the fix really did the right thing. The result shows on the fix as a passed or failed outside check.

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": {
      "fix_id": "<fix_id>",
      "what": "<what>",
      "test": "<test>"
    },
    "name": "add_check"
  }
}

Input Schema

Name	Required	Description
`test`	Yes	Bash, run in the fix's repro project after its setup and apply. Exit 0 = the fix is right, non-zero = it isn't.
`what`	Yes	One line: what your check proves, e.g. 'valid rows are still imported and the bad row is reported'.
`fix_id`	Yes	The fix to check.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 25, 2026

TDQS

A4.1/5.0

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 the execution model (Yarrow runs the fix's setup and apply in a clean sandbox, then the test), the success contract (exit 0 only if the fix is right), and where the result surfaces (passed/failed outside check on the fix). It omits permissions, idempotency/repeatability, and runtime expectations.

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 with the core action, then rationale, then execution semantics; four sentences that each contribute. There is mild overlap between 'Add your own test' and the later restatement of the exit-0 contract, but nothing is wasted.

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 3-required-param mutation with no annotations and no output schema, the description covers what the tool does, where the test executes, how success is determined, and how the outcome is reported. An agent could call it correctly; only auth/prerequisite details and result retrieval are unstated.

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%, so all three parameters are already documented in the schema, making 3 the baseline. The description reinforces the exit-0 contract for 'test' and the sandbox context in which it runs, but adds no format or content guidance for 'what' or 'fix_id' beyond what the schema states.

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 ('Add your own test to someone else's fix') and immediately defines the artifact it creates: an outside check attached to a fix. No sibling tool (get_fix, search_fixes, report_outcome, share_fix) does this, so an agent can distinguish it without opening any 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?

Gives explicit selection guidance with a concrete trigger: use it when the fix's own test is too easy, illustrated by 'only checks that nothing crashes when it should also check that the valid data survived.' It does not state a when-not condition (e.g., the fix's own test is already adequate), so it stops short of full routing guidance.

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

All Yarrow tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?