get_domainsLists custom domains: with site, the ones on it with status and DNS records (pending ones re-checked live); with query, likely-available names to buy at a registrar (Page Lemon sells none).
| Name | Required | Description | Default |
|---|---|---|---|
| site | No | ||
| tlds | No | With query: endings to check, e.g. ["com","co.uk"] | |
| query | No | A name, idea or domain to find, e.g. Maison Cafe |
| Name | Required | Description | Default |
|---|---|---|---|
| domains | No |
Changes observed during successful MCP inspections.
Input schema / properties / query / descriptionPrevious value: -"Finding one: a name, idea or domain, e.g. Maison Cafe or maisoncafe.co.uk"New value: +"A name, idea or domain to find, e.g. Maison Cafe"Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "domains": {
+ "type": "array"
+ }
+ },
+ "type": "object"
+}Input schema / properties / site / descriptionRemoved value: -"Site name"Input schema / properties / site / descriptionPrevious value: -"Site name, e.g. brave-otter-4821"New value: +"Site name"Output schema / (root)Previous value: -{
- "additionalProperties": {},
- "properties": {
- "agent_message": {
- "type": "string"
- },
- "confirm_token": {
- "type": "string"
- },
- "error": {
- "description": "On failure (isError): {code, message}"
- }
- },
- "type": "object"
-}New value: +nullDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description still adds real value by disclosing that pending domains are re-checked live (latency/side-effect nuance) and that no domain can actually be purchased here. It says nothing about result limits or what an empty lookup returns.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single dense sentence with zero filler, front-loaded with the object of the operation before the two mode branches. The telegraphic 'with site, the ones on it' phrasing is efficient but slightly clipped.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values need no explanation, and the description still flags status and DNS records as payload. For a three-param, no-required-param read tool this is nearly sufficient; only the tlds interaction and multi-param combination behavior are left open.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description gives meaning to 'site' (which the schema leaves undocumented) and to 'query'. However it never mentions 'tlds', the third parameter, so the agent must infer from the schema that it only applies alongside 'query' and what happens if both 'site' and 'query' are supplied. With 67% schema coverage this is roughly baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Lists custom domains') and immediately splits the tool into its two distinct modes, tied to the 'site' and 'query' parameters. An agent can tell this apart from the mutation siblings add_domain/remove_domain without opening any schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly routes the agent: pass 'site' to inspect domains already on a site, pass 'query' to discover names available to buy. The parenthetical '(Page Lemon sells none)' heads off a wrong assumption about purchasing. It does not name the mutation siblings it should be paired with when the intent is to add or remove.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.