Skip to main content
Glama

Propose the checks that verify a code change

plan_verification

Proposes which existing Recovery Probe checks verify a Git change by matching changed files and suspects against the scenario registry; it runs nothing and returns a plan, not a verdict.

Instructions

Experimental. Before recording a baseline, proposes which existing Recovery Probe checks verify a change: it matches the files changed since a Git reference (committed, staged, unstaged, untracked, deleted, renamed) against the project scenario registry (recovery-probe.registry.json) and the suspects on the changed lines. Each check says which file selected it, what it checks, where its expectation came from and what it does not cover. It also lists suggestions to review, changed files with no known check, and what needs a person: open questions, missing expectations, invalid entries. It runs nothing. The result is a proposal, never a verdict: no matching check does not mean the change is safe. Resolve needsInput, then record the baseline with verify_change from the version before the change.

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": "plan_verification"
  }
}

Input Schema

NameRequiredDescriptionDefault
baseNoThe Git reference the change starts from.main
runsNoRuns of each check on each side in the candidate plan. Default: 3.
taskNoWhat the change is for, kept in the report as given.
forceNoReplace an existing plan file. Only after reviewing it.
writeNoWrite the candidate verify plan to this relative path, such as .recovery-probe/verify.json.
registryNoThe scenario registry, relative to the working directory. Default: recovery-probe.registry.json.
expectationsNoExpected behavior, and where it comes from, for registry scenarios that state none, by scenario name. Only what the user said; never invent one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.3

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false but destructiveHint=false; the description reconciles this by stating 'It runs nothing' and that output is a proposal, not a verdict, while the write/force params explain the file-mutation side. It could go further on whether writing is required, but it adds substantial behavioral context beyond the annotations.

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 status ('Experimental') and the core action, and every sentence carries information about behavior or output contents. It is dense and slightly long, but not padded with repetition.

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 7-parameter tool with no output schema, the description compensates well by enumerating what the result contains: per-check selection rationale, suggestions to review, unverified changed files, and human-action items. An agent can set expectations without a return-value schema.

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; however the description adds real meaning by explaining that base defines files changed since a Git reference and that inputs are matched against the registry and changed-line suspects. The expectations parameter's constraint ('Only what the user said; never invent one') is reinforced in prose.

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 ('proposes which existing Recovery Probe checks verify a change') and immediately scopes it: it matches changed files since a Git reference against the registry and suspects. It is clearly distinct from verify_change, which it names as the separate baseline-recording step.

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 explicit timing ('Before recording a baseline'), an explicit workflow ('Resolve needsInput, then record the baseline with verify_change from the version before the change'), and an explicit caution that no matching check does not mean the change is safe. The agent knows both when to call it and what to do next.

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