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

Annotations declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, yet the description attributes "create ... or change" of a SIP connection and its numbers to this tool and discusses attaching numbers. That is a direct conflict with the declared read-only, non-destructive profile. The one genuinely useful disclosure ("Passwords are write-only and never returned") does not offset the 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 single run-on paragraph leads with service boilerplate and crammed sibling-tool behavior (rate limits, billed calls, SIP OPTIONS) instead of front-loading what this tool returns. Much of the text does not earn its place because it belongs to the descriptions of other tools in the family.

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?

With no output schema, the description is the only place an agent can learn what a retrieved SIP connection looks like, and it says nothing about returned fields, pagination of numbers, or error behavior for unknown or unauthorized connection_id. For a three-parameter read tool with zero schema documentation, the description leaves essential invocation details unaddressed.

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?

Schema description coverage is 0% for three parameters, so the description must carry the burden and does not. connection_id, project_id, and especially offset (an odd parameter for a single-resource get, presumably paginating the attached numbers) receive no explanation. The phrase "and its numbers" hints at pagination but never states what offset controls or its unit.

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 opens with a service-level claim ("Bring your own SIP trunk: create, read or change a carrier SIP connection and its numbers") rather than stating that this tool retrieves one connection by connection_id. The read action is one of three verbs listed, so an agent cannot tell from the text whether get_sip_connection fetches, creates, or mutates a connection. Only the tool name disambiguates it from create_sip_connection and update_sip_connection.

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 routing guidance present (check_sip_connection_number_ownership places a verification call, start_sip_connection_test_call places a billed call, check_sip_connection_reachability sends SIP OPTIONS) describes sibling tools rather than when to choose this one. Nothing says when to use get_sip_connection instead of list_sip_connections, get_sip_connection_ownership_check, or update_sip_connection, and no prerequisites are stated.

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