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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is known; the description adds genuine value beyond them by clarifying that the contact itself is not deleted, that false is a no-op per role, and that removal can cause downstream registration validation failures. What it doesn't say is what happens if all four flags are false, or whether re-removing an already-removed role errors.

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 tight sentences: the action first, then the flag mechanics, then the failure mode and remediation. Given 0% schema coverage, the middle sentence about the booleans is doing necessary work rather than padding.

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 destructive mutation with an output schema and full annotations, this covers action, scope, side effects, and a remediation path, which is nearly everything an agent needs. The remaining gaps are the all-false edge case and repeat-call behavior, neither of which is fatal.

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?

With schema coverage at 0% the description must carry the load, and it does: each of the four booleans is tied to a named registrant/admin/technical/billing role and given explicit true/false semantics, and contact_handle is described as an existing handle the roles are removed from. Nothing about the five parameters is left ambiguous.

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 (remove), a specific resource (default domain-registration roles), and a bound scope (one existing contact handle), so it is clearly distinguishable from the sibling assign_domain_registration_contact_roles. It stops short of naming that sibling explicitly as the counterpart operation, so it falls just under a 5.

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?

Explains exactly how to invoke the flags (set one or more of remove_registrant/admin/technical/billing to true; false leaves the role unchanged) and warns that removing a role without reassignment can break registration validation unless register_domain is called with an explicit registration-ready contact_handle. That is a real when/how-not signal, though it never points to assign_domain_registration_contact_roles as the way to move a role to a different contact.

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