Skip to main content
Glama
Sign In

Squish

by co.squish
OverviewDiscussionsAdmin

Advance email migration

advance_email_migration

Drive a migration to its next stage. Use after the customer has done their part on a polled stage — e.g. they just clicked the Microsoft consent URL and we need to re-check whether admin access has been granted, or a stage previously failed and they want to retry. Idempotent — safe to call multiple times. Returns the new state (or NOT_READY if the upstream signal hasn't arrived yet — that's normal, tell the user to wait a bit). Confirm-first is NOT required here because this tool doesn't cross a "money moves" boundary on its own — order placement happens at Confirm email migration (in the Squish dashboard), not here.

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": {
      "migrationId": "<migrationId>"
    },
    "name": "advance_email_migration"
  }
}

Input Schema

NameRequiredDescriptionDefault
migrationIdYesThe migration ID to advance.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.5/5.0
Behavior1/5

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

The description states 'Idempotent — safe to call multiple times', but the supplied annotations declare idempotentHint: false. That is a direct contradiction of the exact same property, and it is material: an agent trusting the prose may re-call and push the migration forward twice. The otherwise useful detail (NOT_READY return, no confirm-first needed, order placement deferred) does not offset a contradiction on a safety-relevant hint.

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 core action, then triggers, then return behavior, then the safety-boundary caveat — a logical progression with little waste. The confirm-first explanation is slightly long-winded but does carry real decision value.

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 one-parameter state-advancing tool with no output schema, the description covers return values (new state or NOT_READY), retry semantics, and where the money-moving boundary sits. Only the absence of guidance on polling/next step after NOT_READY leaves a small gap.

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?

There is a single required parameter with 100% schema coverage that already documents migrationId. The description adds no format, sourcing, or lookup guidance beyond the schema, so baseline 3 applies.

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?

'Drive a migration to its next stage' is a specific verb+resource, and the surrounding sentences make it clearly distinct from read-only siblings like get_migration_status and list_my_migrations. An agent knows this mutates migration state rather than just reading it.

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?

Strong trigger conditions: use after the customer completes a polled step (e.g. clicking the Microsoft consent URL) or to retry a previously failed stage. It stops short of explicitly naming the sibling to poll first (get_migration_status) or what to do if NOT_READY persists, but the when-to-call guidance is concrete and actionable.

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

All Squish toolsInspect
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