Skysay

Update sip connection

update_sip_connection

Destructive

Bring your own SIP trunk: create, read or change a carrier SIP connection and its numbers through the same service as /v1/sip-connections. Passwords are write-only and never returned. Attaching a number for incoming calls, and check_sip_connection_number_ownership, place one Skysay verification call to that number (rate limited per number and per workspace); outbound with the number is refused until its ownership is confirmed. start_sip_connection_test_call places one billed call (calls:write) from the number to the given phone; check_sip_connection_reachability sends one SIP OPTIONS to the carrier server. No carrier settings change.

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>",
      "country": "<country>",
      "expected_revision": "<expected_revision>",
      "connection_id": "<connection_id>"
    },
    "name": "update_sip_connection"
  }
}

Input Schema

Name	Required	Description
`name`	Yes
`codecs`	No
`country`	Yes	The carrier's country, used for national number formats.
`inbound`	No
`outbound`	No
`project_id`	No
`channel_limit`	No	Recorded and shown; your carrier enforces it.
`connection_id`	Yes
`expected_revision`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

C2.9/5.0

Behavior4/5

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

Annotations already declare destructive, non-idempotent, open-world behavior, and the description adds real value beyond them: passwords are write-only and never returned, ownership-check calls are rate limited per number and workspace, outbound is refused until ownership is confirmed, and the test call is billed. The closing "No carrier settings change" is ambiguous for an update tool but not a direct contradiction of the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is front-loaded with a confused create/read/change framing, then spends most of its length on side effects of sibling tools instead of this tool's own contract. Those sentences may inform the agent about related tools, but they do not earn their place in this definition.

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?

Placeholder.

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

Parameters2/5

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

Schema description coverage is only 22% across 9 parameters, so the description carries a compensation burden it does not meet. It says nothing about the required expected_revision (optimistic concurrency), connection_id, project_id, channel_limit, codecs, or whether inbound/outbound are full replacements or partial updates. The only parameter-adjacent statement, that passwords are write-only, merely restates the schema's writeOnly flag.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening names a verb and resource ("change a carrier SIP connection and its numbers") but immediately muddles it by claiming the tool can "create, read or change," which is not what update_sip_connection should do. The bulk of the text then describes sibling tools (attach number, test call, reachability) rather than this operation, so the agent must infer the actual scope. Sibling differentiation is present for other tools, not for this one vs create_sip_connection or save_sip_connection_dial_format.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to call update_sip_connection rather than create_sip_connection, disable_sip_connection, or save_sip_connection_dial_format. The description explains side effects of neighbouring tools (verification calls, billed test calls) but never states conditions or exclusions for using this tool itself.

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

All Skysay 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.