Skip to main content
Glama

Check registered scenarios before relying on them

self_check_scenarios
Destructive

Validate recovery-probe scenario registry entries before verification: inspect commands, files, placeholders, and config without running, or execute passing scenarios against a reference build.

Instructions

Experimental. Checks scenarios from the project registry (recovery-probe.registry.json) before they are used for before/after verification. Without run it only looks: the command line of each check as its command parses it, its files, unfilled placeholders, and its configuration against the validators its command uses; nothing is started or contacted. With run true it runs each scenario that passes against the application running now, which the user declares as the reference build in reference; never pick that yourself. Each run injects the faults and performs the actions its configuration names. Each scenario ends configuration-error, execution-failed, incomplete, inconsistent, findings (on the reference build) or clean. invalidEntries lists the registry entries it could not check, and passed is false while one of them concerns the selection. Clean never means the app is correct, the scenario detects its defect, or a change is verified; report outcomes and guidance as they are.

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": "self_check_scenarios"
  }
}

Input Schema

NameRequiredDescriptionDefault
runNoRun the scenarios against the running application. Only when the user asked for it and named the reference build.
runsNoRuns of each scenario with run. Default: 3.
registryNoThe scenario registry, relative to the working directory. Default: recovery-probe.registry.json.
referenceNoRequired with run: the build the user says is running, such as a commit or version. Kept as given; not verified.
scenariosNoRegistry scenario names. Default: every registered check.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.3

TDQS

A4.3/5.0
Behavior5/5

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

Annotations mark this destructive and non-read-only; the description explains exactly why (each run injects faults and performs configured actions against the live app) while the default path contacts nothing. It also enumerates terminal states, discloses invalidEntries and the semantics of passed=false, and caps the meaning of 'clean' — all context the annotations cannot carry.

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 'Experimental' and the purpose, then the two modes; every sentence carries decision-relevant information. It is dense to the point of cramming multiple clauses per sentence, which costs some readability, but there is no filler.

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?

For a destructive, five-parameter tool with no output schema, the description covers mode selection, preconditions, the shape of outcomes, failure reporting, and interpretation caveats. Nothing an agent needs in order to call it safely and read its result is missing.

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 the baseline is 3; the description still adds real meaning by tying run to the requirement that the user name the reference build, and by forbidding the agent from choosing `reference` itself. Less is said about runs, scenarios and registry beyond their defaults, but those are documented in the schema.

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 resource — checks registered scenarios from recovery-probe.registry.json before they are used for before/after verification — and splits the behavior into a look-only mode and a run mode. It is clear what the tool does, though it never contrasts itself directly with the sibling probe/verification tools.

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 when-to-use ('before they are used for before/after verification'), an explicit when-not default ('Without run it only looks... nothing is started or contacted'), and a hard precondition for the risky path ('only when the user asked for it and named the reference build', 'never pick that yourself'). What is missing is any named alternative tool for the execute-scenarios case.

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