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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered. Beyond that the description only adds that a DNS workflow is involved via the instructions tool; it doesn't say what actually happens after the call (DNS record creation, propagation, when verification becomes possible) or whether re-calling is safe. It contributes useful direction but little behavioral depth.

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?

Three short sentences, front-loaded with the action, then parameters, then the hand-off to the instructions tool. The trailing "MCP version 2.12." fragment is terse but useful for populating mcp_version. No wasted prose.

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 4-parameter, fully documented, annotated tool with no output schema, the description covers what an agent needs to invoke it and points to the workflow tool for anything further. The main remaining gap is that the post-call path (verify_custom_domain) is not surfaced here, deferred entirely to get_custom_domain_instructions.

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 100%, so all four parameters are already documented, including the enum values and the mcp_version pattern. The description restates the required parameters and the two dns_mode values, which duplicates rather than extends the schema. The one additive detail is pinning MCP version 2.12, already present in the mcp_version schema description, so the baseline 3 is appropriate.

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: "connect a domain to an app," which is clearly an additive operation distinct from siblings named delete_custom_domain and verify_custom_domain. The required parameters are named, so the agent understands the shape of the call. It stops short of explicitly contrasting itself with those siblings, but the name plus verb make the intent unambiguous.

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: "Call get_custom_domain_instructions for usage and workflow," which tells the caller that prerequisite/workflow knowledge lives in a sibling tool. It gives clear triggering context (connecting a domain to an app) but no when-not-to-use conditions and doesn't mention verify_custom_domain as a follow-up step, leaving that to the instructions tool.

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