Skip to main content
Glama

Prepare changing the resolver

set_resolver
Read-onlyIdempotent

Prepare changing an ENS name's resolver, the contract that holds its records, for the user to sign in their own wallet, e.g. 'Set nick.eth's resolver to the public resolver'. Nothing is sent. Records on the old resolver stop resolving.

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": {
      "name": "<name>",
      "account": "<account>",
      "resolver": "<resolver>"
    },
    "name": "set_resolver"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesENS name as the user wrote it, e.g. nick.eth; normalised by the server (ENSIP-15)
accountYesAccount that will sign the transactions: an address (0x…) or an ENS name
resolverYesA resolver address, default (the ENSv1 public resolver) or none

Output Schema

NameRequiredDescriptionDefault
costYes
planYesHandle of this plan for get_plan; pass it back unchanged
callsYesUnsigned calls, in order, for the account's wallet
chainYes
stepsYes
issuesYesWhy a checked step would fail
accountYes
deploysNoContracts the plan deploys, at addresses known in advance
signingYesHow to sign the steps, in plain words
summaryYes
warningsYes
willSucceedYesWhether the steps that can be checked now would succeed if signed now
requirementsYesWhat the account needs before signing, e.g. a token balance

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well beyond the annotations by explaining that the tool only prepares an unsigned transaction ('Nothing is sent'), which is the key fact an agent needs and directly supports readOnlyHint=true. It also discloses a downstream consequence the annotations do not cover at all: 'Records on the old resolver stop resolving' — warning of an effect that is invisible in destructiveHint=false, without contradicting it, since the tool itself performs no mutation.

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?

Three short sentences, front-loaded with the action, followed by the wallet-signing context and the consequence warning — no filler. The example is embedded mid-sentence, which is slightly less scannable than trailing it, but overall the phrasing earns its space.

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?

With an output schema present, return values need no explanation, and the description covers what the tool does, that it sends nothing, and the effect on old records. The only modest gap is that it doesn't mention preconditions (valid ownership/permissions on the name) that determine whether preparing the change is sensible.

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?

Schema coverage is 100%, so all three parameters are already documented in structured form, giving a baseline of 3. The description only loosely reinforces the resolver parameter through the 'public resolver' example and says nothing extra about the 'none' option or the account parameter, so it adds little meaning beyond the schema.

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+resource ('Prepare changing an ENS name's resolver') and immediately defines the resource as 'the contract that holds its records', which is exactly the distinction that separates it from set_records. The concrete example ('Set nick.eth's resolver to the public resolver') leaves no ambiguity about the operation.

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 phrase 'for the user to sign in their own wallet' implies the intended workflow (prepare-then-sign), and 'Nothing is sent' implies this is the pre-broadcast half of a two-step flow. However, no sibling is named as an alternative and no prerequisites (e.g. ownership or permission requirements) are stated, so the guidance is implied rather than explicit.

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.