Skip to main content
Glama

Change a resource's plan

set_resource_plan
Idempotent

Move a resource, such as a database, to another plan in place. Its data and environment variables stay the same, and attached apps do not restart. A plan change can change what the resource costs, so first call with preview set to true, show the person what changes, and change the plan only once they confirm. The preview lists each limit's current use and its value on both plans, and says what an attached app notices while the change applies. Every answer names from_plan, to_plan, and a status: previewed, applied, or pending with the reason the move has not finished. A move to a plan the resource would not fit is refused and changes nothing. A private system's plan changes only once an org Admin approves it: the call answers requested with a request whose url to give the person, and nothing changes until then. list_catalog_resources names the plans. Requires connecting a Valet account.

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": {
      "resource": "<resource>",
      "plan": "<plan>"
    },
    "name": "set_resource_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
planYesThe plan to move to, as list_catalog_resources names it.
previewNoReport what the change would do without making it. Preview first and confirm with the person before changing the plan.
org_nameNoThe Valet organization the resource belongs to. Omit to use the organization the account joined first.
resourceYesThe resource's name in the organization.

Output Schema

NameRequiredDescriptionDefault
orgYesName of the Valet organization the resource belongs to.
limitsNoSet on a preview: each limit's current use and its value on both plans.
reasonNoSet when pending: why the last attempt did not finish.
statusYespreviewed when nothing changed, applied when the resource is on to_plan, pending when Valet accepted the change and is still applying it, or requested when the resource is a private system and an org Admin must approve the change first; nothing changed yet.
requestNoSet when requested: the access request an org Admin approves before the plan changes. Give the person its url and follow it with get_request.
to_planYesThe plan asked for.
resourceYesName of the resource.
from_planYesThe plan the resource was on.
interruptionNoSet on a preview: what an attached app notices while the change applies. Absent when it notices nothing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedOutput schema / properties / request
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Set when requested: the access request an org Admin approves before the plan changes. Give the person its url and follow it with get_request.",
      +  "properties": {
      +    "expires_at": {
      +      "description": "When the request expires unanswered, as an RFC 3339 UTC time.",
      +      "type": "string"
      +    },
      +    "fields": {
      +      "description": "Names of what the person enters, never values.",
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": [
      +        "null",
      +        "array"
      +      ]
      +    },
      +    "id": {
      +      "description": "Id of the request. Pass it to get_request to follow the request.",
      +      "type": "string"
      +    },
      +    "next_step": {
      +      "description": "What to do next: give the person the url, then follow the request with get_request.",
      +      "type": "string"
      +    },
      +    "url": {
      +      "description": "Dashboard page to give the person. They open it signed in to Valet to complete the request. It holds no credential.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "id",
      +    "url",
      +    "expires_at",
      +    "fields",
      +    "next_step"
      +  ],
      +  "type": [
      +    "null",
      +    "object"
      +  ]
      +}
    • changedOutput schema / properties / status / description
      Previous value: -"previewed when nothing changed, applied when the resource is on to_plan, or pending when Valet accepted the change and is still applying it."New value: +"previewed when nothing changed, applied when the resource is on to_plan, pending when Valet accepted the change and is still applying it, or requested when the resource is a private system and an org Admin must approve the change first; nothing changed yet."
  2. Added

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the annotations (readOnly=false, destructive=false, idempotent=true), the description discloses substantial behavior: data and env vars preserved, attached apps don't restart, cost may change, fit-check refusal changes nothing, and private systems require org Admin approval yielding a "requested" status with a URL. It also discloses the account-connection prerequisite. These materially exceed what the annotations convey, though the exact response payload shape is left to the output schema.

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?

Content is front-loaded with the core action and keeps the safety-critical preview/confirm workflow prominent. It is dense and long-ish (statuses, refusal, approval, prerequisite), but nearly every sentence carries operational weight; only minor tightening is possible.

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 mutating, multi-outcome tool it covers the important cases: preview, apply, pending, refused-by-fit, and admin-approval request. An output schema exists so return-value detail is rightly delegated, leaving only minor gaps such as how a pending move is later resolved.

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, but the description adds meaning beyond the field docs: it explains why preview should be set, that plan names come from list_catalog_resources, and that org scope interacts with private-system approval. That is genuine added context rather than repetition.

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?

The description opens with a specific verb and resource ("Move a resource, such as a database, to another plan in place") and immediately distinguishes itself from list_catalog_resources by assigning plan enumeration to that sibling. An agent can tell exactly what this tool does without opening the schema.

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?

It prescribes explicit when-to-use workflow: call with preview true first, show the person the changes, and only apply after they confirm. It also names the alternative for finding plans (list_catalog_resources) and states the private-system approval path, so nothing about sequencing is left to inference.

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.

Resources