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

Annotations only declare it as a non-read-only, non-idempotent, open-world write, so the description adds real value beyond them: write-only passwords that are never returned, per-number and per-workspace rate limits on verification calls, refusal of outbound until ownership is confirmed, and billed test calls requiring calls:write. It stops short of describing the resulting connection state or what happens on partial failure, but the behavioral picture is substantially richer than the annotations alone.

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 purpose is front-loaded, which is good, but the bulk of the text describes sibling tools' behavior (verification calls, billed test calls, SIP OPTIONS) rather than the creation operation itself. The final "No carrier settings change" sentence is terse and ambiguous. The content is dense and mostly earns its place as routing context, but the balance is off for a create tool.

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 7-parameter creation tool with no output schema and low top-level parameter coverage, the description leaves important gaps: what is returned after creation (connection ID, status), how inbound vs. outbound configuration relates, and whether creation itself consumes numbers or requires prior authorization. Without an output schema, the description should have said what the caller gets back, and it does not.

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?

Top-level schema description coverage is 29% (name, codecs, inbound, outbound, project_id carry no top-level description), so the description is expected to compensate. It only adds that passwords are write-only and never returned; the remaining meaning for name, codecs, project_id, and the inbound/outbound split comes from the nested schema descriptions, which are fairly detailed. The description contributes marginally to parameter meaning.

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?

Opens with a specific verb+resource framing ("Bring your own SIP trunk: create ... a carrier SIP connection") that identifies the resource and its domain. It is slightly muddied by the claim of "create, read or change ... through the same service as /v1/sip-connections," which blurs the boundary with get_sip_connection and update_sip_connection, but the creation intent still comes through.

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 routes the agent for follow-up operations (check_sip_connection_number_ownership, start_sip_connection_test_call, check_sip_connection_reachability) and states constraints such as ownership-confirmation gating for outbound. However, it never says when to prefer this tool over update_sip_connection, get_sip_connection, or list_sip_connections, and the "read or change" phrasing actively invites confusion about which sibling handles modification.

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