Skip to main content
Glama

Name Whisper — ENS Intelligence Layer

by ai.namewhisper
OverviewDiscussionsAdmin

renew_ens_name

Destructive

Renew an ENS name or batch of names. Returns the transaction data needed to extend registration.

Unlike registration, renewal is simple — just one transaction with payment. No commit/reveal needed.

Accepts any duration from 1 day up — days, weeks, months, years. ENS protocol has no minimum renewal period; this tool floors at 1 day for safety. Examples: 1 day, 7 days (1 week), 28 days (1 month), 365 days (1 year).

Anyone can renew any name (you don't need to be the owner). This is useful for:

  • Extending your own names before expiry

  • Gifting renewal to a friend's name

  • Protecting valuable names from expiring

Returns exact on-chain pricing from the ETHRegistrarController with a 5% buffer (excess is refunded) — do NOT estimate renewal prices yourself.

For batch renewals (multiple names), all names are bundled into a SINGLE Multicall3 transaction.

Calling this tool never spends money — it only builds an unsigned transaction rendered as a sign-card; nothing happens until the user clicks Sign. So the sign-card IS the confirmation step.

Conversational flow:

  • User names the specific name(s) ("renew coffee.eth", "renew coffee.eth for 3 months"): call this tool IMMEDIATELY. If no duration was given, use the 1-year default and say so ("built it for 1 year — tell me if you want longer/shorter") — do NOT stop to ask the duration first; they can just say a different one and you rebuild.

  • User names a BUDGET ("renew coffee.eth for $45", "put 0.02 ETH into it", "I only have ETH for $45"): pass budgetUsd / budgetEth and NO duration. The tool solves the duration from live on-chain pricing — do not work it out yourself (a 4-character name costs ~$160/yr, a 3-character ~$640/yr; the model got the tier wrong live and quoted 26 days for a 4-char name that $45 actually renews for ~100 days). A budget is a HARD CAP: never rebuild above it to "save the name" or reach Active. If the capped renewal leaves the name in grace, the result's budget.summary says so — relay that ONE sentence and hand over the card. Never call this tool more than once for the same budget.

  • Every result carries whatThisBuys — the new expiry DATE and days from now. That sentence is what you quote before and AFTER the transaction, never the duration ("locked in for 90 days" was said live about a renewal that bought 2 days: it extends from the ORIGINAL expiry).

  • Open-ended "renew my names" / "bulk renew" with no list: first call get_wallet_portfolio to find the names, IGNORE every EXPIRED and PREMIUM_AUCTION name (renewing those reverts the whole batch), present a numbered list grouped by urgency, and ask which names + what duration. Only THEN call this tool.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
namesYesENS name or array of names to renew (e.g. "coffee.eth" or ["coffee.eth", "wallet.eth"])
yearsNoDEPRECATED — use duration instead. Number of years (converted to days internally).
durationNoDuration in days to extend registration (e.g. 7 for 1 week, 28 for a month, 365 for a year). Default: 365. Minimum: 1 day. Maximum: 36500 (100 years). When a budget is also given, the budget wins: the duration is capped to what the budget covers.
budgetEthNoSpend cap in ETH ("renew X with 0.02 ETH", "I only have 0.05 ETH"). Same behaviour as budgetUsd. Mutually exclusive with budgetUsd.
budgetUsdNoSpend cap in USD ("renew X for $45", "put $20 into it"). The tool prices the name(s) on-chain and picks the LONGEST whole number of days whose transaction value fits under this cap — never compute the duration yourself from a budget. Mutually exclusive with budgetEth.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / budgetEth
      Added value: +{
+  "description": "Spend cap in ETH (\"renew X with 0.02 ETH\", \"I only have 0.05 ETH\"). Same behaviour as budgetUsd. Mutually exclusive with budgetUsd.",
+  "exclusiveMinimum": 0,
+  "type": "number"
+}
    • addedInput schema / properties / budgetUsd
      Added value: +{
+  "description": "Spend cap in USD (\"renew X for $45\", \"put $20 into it\"). The tool prices the name(s) on-chain and picks the LONGEST whole number of days whose transaction value fits under this cap — never compute the duration yourself from a budget. Mutually exclusive with budgetEth.",
+  "exclusiveMinimum": 0,
+  "type": "number"
+}
    • changedInput schema / properties / duration / description
      Previous value: -"Duration in days to extend registration (e.g. 7 for 1 week, 28 for a month, 365 for a year). Default: 365. Minimum: 1 day. Maximum: 36500 (100 years)."New value: +"Duration in days to extend registration (e.g. 7 for 1 week, 28 for a month, 365 for a year). Default: 365. Minimum: 1 day. Maximum: 36500 (100 years). When a budget is also given, the budget wins: the duration is capped to what the budget covers."
  2. Changed4 schema fields changed
    • changedInput schema / properties / duration / description
      Previous value: -"Duration in days to extend registration (e.g. 7 for 1 week, 28 for a month, 365 for a year). Default: 365. Any positive number is valid — there is NO minimum."New value: +"Duration in days to extend registration (e.g. 7 for 1 week, 28 for a month, 365 for a year). Default: 365. Minimum: 1 day. Maximum: 36500 (100 years)."
    • addedInput schema / properties / duration / maximum
      Added value: +36500
    • addedInput schema / properties / duration / minimum
      Added value: +1
    • changedInput schema / properties / duration / type
      Previous value: -"number"New value: +"integer"
  3. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Adds major context beyond annotations: builds an unsigned sign-card and spends no money until sign, applies a 5% pricing buffer, bundles batch renewals into one Multicall3 transaction, and reverts the batch if expired/premium names are included. No contradiction with destructiveHint; the description clarifies when the actual side effect happens.

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?

Long but well-structured and front-loaded with core behavior; behavioral essentials appear before the conversational-flow patterns. Slight redundancy (e.g., duration examples repeated with schema) and a lengthy live-mistake anecdote keep it from a perfect score.

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?

Despite no output schema, it explains return semantics: transaction data, exact pricing with buffer, sign-card output, and the whatThisBuys expiry-date message to quote. Covers edge flows like budgets, grace periods, and batch reverts, making it complete for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even with 100% schema coverage, the description enriches every parameter: duration default/min/max behavior, budget as a hard cap that overrides duration, mutual exclusivity of budgetEth/budgetUsd, and the deprecated years field. It tells the agent exactly how to map user phrases to parameters.

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 ('Renew') and resource ('ENS name or batch of names'), and immediately distinguishes renewal from registration ('Unlike registration... No commit/reveal needed'). This separates it from sibling tools like bulk_register and purchase_name.

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?

Extremely explicit: names-specific requests trigger immediate calling with 1-year default, budget requests pass budgetEth/budgetUsd without duration, open-ended requests first call get_wallet_portfolio and ask. It also warns against estimating prices and repeated budget calls.

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

All Name Whisper — ENS Intelligence Layer 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