SatsDNS

Change DNS records (free, token)

records_change

DestructiveIdempotent

Free: applies up to 100 rrset changes at once, all or none. Each item REPLACEs one rrset (name and type) with the given records, or DELETEs it. Deleting records can take a site or mail offline: change only what your user asked for. Pass the zone token (jdz_...) from the create answer, or a scoped account API key (jdk_...) made in the dashboard. Either passes through your model context and transcript: treat it like a password.

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": {
      "zone": "<zone>",
      "rrsets": "<rrsets>"
    },
    "name": "records_change"
  }
}

Input Schema

Name	Required	Description
`wait`	No	Optional: answer only once both nameservers (ns1 and ns2) serve the change, at most 20 s. The answer's served object says which do; use it before asking an ACME server to check a DNS-01 TXT record.
`zone`	Yes	The hosted zone, e.g. example.com.
`token`	No	The zone token (jdz_...); or give api_key.
`rrsets`	Yes	The changes (at most 100).
`api_key`	No	Instead of token: an account API key (jdk_...) whose scope covers this object (read, or write for changes).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

addedInput schema / properties / wait

Added value: +{
+  "description": "Optional: answer only once both nameservers (ns1 and ns2) serve the change, at most 20 s. The answer's served object says which do; use it before asking an ACME server to check a DNS-01 TXT record.",
+  "type": "boolean"
+}

First observedOct 28, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses atomicity (all-or-none, max 100 items), the real-world consequence of DELETE ('can take a site or mail offline'), and a security warning that the token/API key transits model context and should be treated like a password. These are exactly the traits an agent needs before issuing a destructive mutation, and none are derivable from destructiveHint alone.

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?

Three tight, front-loaded sentences: capability first, hazard second, credential handling third. Every clause carries operational weight and nothing repeats the structured fields.

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?

A destructive, open-world mutation needs the safety and auth context this supplies, and it supplies it well. The one gap is return behavior — the description never says what the response contains (the schema alludes to a 'served' object for wait), though no output schema exists to compensate.

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 already 100%, so the baseline is 3, but the description adds provenance the schema lacks: the token comes from the create answer (jdz_...) and an alternative is a scoped dashboard API key (jdk_...). It does not elaborate on the wait flag or per-item fields, which live entirely in 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 and resource ('applies up to 100 rrset changes'), including the atomic all-or-none semantic and the per-item REPLACE/DELETE behavior. An agent can immediately tell this is the write counterpart to records_list without opening either schema.

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?

Gives clear operative guidance: change only what the user asked for, and the schema-level note ties the wait flag to ACME DNS-01 validation. It never explicitly names records_list as the read-only alternative or states when not to use this tool, which keeps it from a 5.

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

All SatsDNS tools Inspect

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

Need Help?