Check whether one or more TCP ports are open on a host. Pass a single port or a list, up to 10 per call.
| Name | Required | Description | Default |
|---|---|---|---|
| host | Yes | Domain name or host | |
| port | Yes | TCP port, or a list of up to 10 ports, e.g. 443 or [80, 443, 25] |
| Name | Required | Description | Default |
|---|---|---|---|
| ip | No | ||
| ok | No | ||
| host | No | ||
| port | No | ||
| state | No | ||
| timeMs | No | ||
| partial | No | ||
| results | No | ||
| portsRequested | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / port / anyOfAdded value: +[
+ {
+ "maximum": 65535,
+ "minimum": 1,
+ "type": "integer"
+ },
+ {
+ "items": {
+ "maximum": 65535,
+ "minimum": 1,
+ "type": "integer"
+ },
+ "maxItems": 10,
+ "minItems": 1,
+ "type": "array"
+ }
+]Input schema / properties / port / descriptionPrevious value: -"TCP port to test"New value: +"TCP port, or a list of up to 10 ports, e.g. 443 or [80, 443, 25]"Input schema / properties / port / maximumRemoved value: -65535Input schema / properties / port / minimumRemoved value: -1Input schema / properties / port / typeRemoved value: -"integer"Output schema / properties / partialAdded value: +{
+ "anyOf": [
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "null"
+ }
+ ]
+}Output schema / properties / portsRequestedAdded value: +{
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+}Output schema / properties / resultsAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "additionalProperties": {},
+ "properties": {
+ "error": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "ip": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "port": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "state": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "timeMs": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ]
+}Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": {},
+ "properties": {
+ "host": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "ip": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "ok": {
+ "anyOf": [
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "port": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "state": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "timeMs": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already declares this as a safe read operation, so the description does not need to repeat that. The description adds 'up to 10 per call' which is also present in the schema, and does not disclose additional behavioral traits like connection timeouts or return format. It is consistent with annotations, no contradiction.
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?
The description is two short sentences, front-loaded with the primary purpose, and includes a necessary usage hint about the port list limit. Every word earns its place with no redundancy or filler.
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?
For a simple two-parameter read-only tool with full schema descriptions and an output schema, the description provides adequate context for an agent to select and invoke it. Minor omissions like defining 'open' (e.g., TCP handshake success) are covered by the output schema, so the description is sufficiently complete.
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?
Both parameters are fully described in the schema (100% coverage), including an example for the port parameter. The description reinforces the ability to pass a single port or list but does not add meaning beyond the schema. Baseline of 3 is appropriate because the schema handles the heavy lifting.
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?
The description clearly states a specific action ('Check whether one or more TCP ports are open on a host') with a specific resource (TCP ports on a host). It distinguishes from sibling tools by explicitly mentioning TCP ports, which differentiates it from DNS, SSL, ping, and other network checks.
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?
The description implies usage for checking TCP port availability but does not explicitly state when to use it over alternatives or mention exclusions. No comparison to sibling tools like ping_test or check_ssl is provided. Usage context is clear but implicit.
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.
Several tools cluster around overlapping diagnostics, such as asn_lookup vs ip_geolocation and website_status vs response_time/redirect_check/http_headers. Descriptions generally clarify the differences, but the boundaries between some tools are not immediately obvious.
Naming conventions are mixed: check_dns and check_ssl use verb-first, while dkim_check, spf_check, and hsts_check use noun-first. There are also varied styles like dns_propagation, domain_expiry, and whois, making the pattern inconsistent but still readable.
At 20 tools, the server falls into the borderline heavy range. Most tools address a distinct diagnostic need, but some could be consolidated, such as website_status overlapping with response_time and redirect_check.
The toolkit covers the core read-only network/domain diagnostic domain well: DNS, email authentication, SSL/TLS, WHOIS, IP intelligence, and website availability. Minor gaps like traceroute or DNSSEC validation exist, but there are no critical missing operations for the apparent purpose.