Skip to main content
Glama

Replay scenario

core_replay_scenario
Destructive

Replay one spec scenario live in its scratch workspace and return the step-by-step evidence. A replay is not a simulation: the scenario runs through the real registry — same guards, same audit trail — in a throwaway workspace, and the response walks every step: act, command, arguments, expectation, and what actually came back. Show it to someone learning the area; the refusal steps teach more than the happy path. Refreshes the persisted evidence. Effects: scratch workspace wiped and scenario replayed; conformance evidence refreshed.

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": {
      "file": "<file>"
    },
    "name": "core_replay_scenario"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNoSpec area. Defaults to o2c.
fileYesScenario file name, e.g. 02_credit_gate.json. See core_spec_status for the list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds substantial context beyond them: the scratch workspace is wiped, evidence is refreshed, and the run hits the real registry with the same guards and audit trail. It also previews the response contents (act, command, arguments, expectation, actual result), so an agent knows exactly what a destructive call returns.

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 action and the key distinction, then evidence format, then effects — good ordering. The 'Refreshes the persisted evidence' sentence slightly overlaps the closing 'Effects:' line about refreshed conformance evidence, a minor redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return contract itself and does so ('walks every step: act, command, arguments, expectation, and what actually came back'). Combined with explicit destructive effects and the 'real registry, throwaway workspace' framing, an agent has everything needed to call this correctly.

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% and both parameters (area, file) are documented in the schema, including the pointer to core_spec_status for file listings. The description adds nothing about parameter meaning beyond 'one spec scenario', so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and scope: replay one spec scenario in its scratch workspace and return step-by-step evidence. The 'a replay is not a simulation' line removes ambiguity about what the operation actually does. It does not name a sibling (e.g. core_spec_status) as an alternative, so it falls just short of the top mark.

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?

'Show it to someone learning the area; the refusal steps teach more than the happy path' gives a concrete usage context — teaching/demonstration — rather than an implied one. There is no explicit when-not-to-use guidance or named alternative for inspecting scenarios without replaying them.

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.