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

Goes well beyond the annotations: a new registrant must confirm by email within 15 days or the domain stops resolving, and the write may be immediate or deferred to an approval queue. It also names the state field that reveals which path was taken, which the schema and annotations do not convey.

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?

Four tight sentences ordered by required-parameter, consequence, then execution timing — no filler. The closing "workflow.state says which" is telegraphic and could read as an incomplete sentence, but it still earns its place by pointing at the discriminator.

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 2-parameter mutation with no output schema, it covers the critical risk (registrant verification lapse taking the domain down) and the async path. The one meaningful gap is whether unspecified roles are preserved or replaced — an agent cannot tell if omitting `admin` wipes the existing admin contact.

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 effectively 0% for the nested contact objects, so the description has to carry meaning. It does add role semantics (registrant is the legal holder and is required; admin/tech/billing are optional), but says nothing about how the four role objects relate, whether omitting a role clears it, or what contact fields are accepted.

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?

"Change contacts" names a verb and resource, and the follow-up sentence pins down that this is the domain's contact set (registrant/admin/tech/billing). It never states the scope word "domain contact" up front and does not contrast itself with the nearby save_registrant or get_registrant siblings, so an agent must infer the boundary.

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?

It clearly says when the change applies immediately (acting for an owner/admin with agent-apply enabled, the default) versus when it queues in list_approvals, and points to workflow.state as the discriminator. What's missing is guidance against the obvious alternative, e.g. when to use save_registrant instead of this tool.

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