Skip to main content
Glama

migration_audit

Run database verification checks and retrieve migration risk comparison reports to validate upgrades and review promotion verdicts before deployment.

Instructions

Run database verification checks and retrieve stored risk comparison reports.

Actions:

  • 'run_check': Run declared check (e.g. post-upgrade queries) against a target or copy.

  • 'list_reports': List recent migration risk comparison reports and promotion verdicts.

  • 'get_report': Fetch paginated findings of a specific report filtered by severity.

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": {
      "action": "<action>"
    },
    "name": "migration_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
dbNoTarget database
pageNoPage number (50 items/page)
checkNoDeclared check name from policy
limitNoReport list limit
actionYes
confirmNoApproval flag for may_modify checks
categoryNoFinding category filter
severityNoSeverity filter
report_idNoReport identifier

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.3

TDQS

A3.6/5.0
Behavior3/5

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

Annotations establish this is not read-only and not idempotent, and the phrase 'against a target or copy' hints that a check can touch live data. But the description never discloses that some checks may modify the target and require the confirm approval flag that appears in the schema, which is the single most consequential behavior for a non-read-only tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single lead sentence plus a three-bullet action list, each bullet a verb-first clause with an example. Nothing is redundant and the mode dispatch is front-loaded where an agent will read it first.

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

Completeness3/5

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

For a nine-parameter, three-mode, non-idempotent tool with an output schema, the description covers the dispatch cleanly but omits the safety-relevant confirm workflow and doesn't state which parameters belong to which action authoritatively. An agent could pick the right action but still call run_check without the approval flag.

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?

With 89% schema coverage the schema already documents each field, yet the action bullets add real meaning by mapping parameters to modes: check names for run_check, report identifiers and severity filtering plus pagination for get_report, and recency limits for list_reports. It leaves category, confirm, and the target/copy selector unexplained, so it stops short of full coverage.

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?

The description names a specific resource (database verification checks and migration risk comparison reports) and enumerates three concrete actions with what each returns. It is clear on its own, but it never distinguishes itself from potential siblings like db_inspect or assess_infrastructure, which could plausibly overlap with verification work.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The action bullets imply the situations each mode serves (post-upgrade checks, reviewing reports, drilling into findings), so usage is inferable. However, there is no explicit when-to-use versus a sibling tool and no stated prerequisites for run_check, such as needing a report to exist before calling get_report.

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