Skael API

Stichprobe bewerten

review_sample

Idempotent

Nimmt das Urteil der Person über die Beispiele eines fertigen Tests auf. Zeig ihr vorher die Beispiele aus get_run_status und frag: Passt das, oder ist etwas falsch drin oder falsch raus? feedback: [] heißt „passt so“ und gibt den Test frei; erst danach geht plan_pipeline_run. Jede Firma, die falsch drin ist (wrong_keep) oder falsch aussortiert wurde (wrong_drop), mit row_id aus den Beispielen und dem Grund in den Worten der Person; daraus entsteht eine neue Fassung, die wieder getestet wird. Kostet nichts.

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": {
      "run_id": "<run_id>",
      "feedback": "<feedback>"
    },
    "name": "review_sample"
  }
}

Input Schema

Name	Required	Description
`run_id`	Yes	ID des fertigen Testlaufs.
`feedback`	Yes	Leer lassen, wenn alles passt.
`organization`	No	Slug der Organisation. Nur nötig, wenn das Werkzeug ORG_AMBIGUOUS meldet.
`accept_despite`	No	Nur wenn die Person trotz eines aussortierten bekannten Kunden oder einer wieder durchgekommenen, als falsch markierten Firma weitermachen will: ["regression"].
`client_request_id`	No	Eigene ID für diesen Aufruf. Dieselbe ID mit denselben Argumenten liefert innerhalb von 24 Stunden das erste Ergebnis, ohne erneut Credits zu kosten.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 6, 2026

changedInput schema / properties / accept_despite / description

Previous value: -"Nur wenn die Person trotz eines aussortierten bekannten Kunden weitermachen will: [\"regression\"]."New value: +"Nur wenn die Person trotz eines aussortierten bekannten Kunden oder einer wieder durchgekommenen, als falsch markierten Firma weitermachen will: [\"regression\"]."

First observedNov 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Beyond the annotations, the description discloses that non-empty feedback produces a new version that must be tested again, that empty feedback releases the test, and that the call costs nothing. That is meaningful behavioral context for a mutating, idempotent tool. It does not describe the response returned, but with no output schema and idempotentHint already declared, the remaining gap is modest.

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?

The core action is front-loaded, followed by the workflow instruction and the semantics of the feedback payload, with the cost note last. A few clauses repeat what the schema's enum descriptions already say (wrong_keep/wrong_drop), but they are woven into a readable flow rather than 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 5-parameter mutation tool with no output schema, the description covers the workflow placement, the releasing condition, the consequence of feedback, and the cost. The main omission is any indication of what the call returns, plus silence on the two exception parameters, which leaves the agent dependent on the schema for edge cases.

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 the schema already documents run_id, feedback, verdict values, organization and accept_despite. The description reinforces the two core semantics (empty list = approval, row_id comes from the examples, reason in the person's own words), but adds nothing about organization, accept_despite or client_request_id. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

The description states a specific action: capturing the person's verdict on the examples of a finished test run, including what an empty feedback list means. It also positions itself in the workflow by naming get_run_status (before) and plan_pipeline_run (after), so an agent can tell it apart from the surrounding siblings.

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?

It gives an explicit precondition ('Zeig ihr vorher die Beispiele aus get_run_status'), the exact question to ask the person, and the sequencing rule that plan_pipeline_run only follows afterwards. The special case is spelled out precisely: feedback: [] means 'passt so' and releases the test.

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

All Skael API 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?