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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=false; the description adds the auth requirement and that the operation targets exactly one registration. The restated idempotency sentence partly duplicates the annotation but spells out its practical meaning. It does not mention error behavior for a stale or invalid registration id, which is the main remaining gap.

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?

Front-loads the auth prerequisite, then the core action, then the optional digest modifier — a sensible order with no filler. The closing idempotency sentence is slightly redundant given the annotation, but it is short and clarifies behavior 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?

With an output schema, full parameter coverage, and rich annotations, the definition covers nearly everything an agent needs to invoke it correctly. Only the failure/validation path for a bad registration_id and the effect on already-queued emails are left implicit.

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%, including the 'omit to keep' semantics for daily_digest and the origin of registration_id, so the schema already does the heavy lifting. The description restates the account-vs-work-email meaning at a high level without adding format or edge-case detail beyond the schema. Baseline 3 applies.

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?

Names a precise verb ('chooses') and a scoped resource ('new referral request emails' for 'one of the user's referrer registrations'), and enumerates the two choices: account vs work email and per-request vs daily digest. An agent can distinguish this from siblings like set_referrer_availability or update_referrer_profile without opening the schema.

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?

States a clear prerequisite ('Requires techjobs.vn sign-in') and clarifies repeat-call behavior ('Calling it again with the same values changes nothing'), which tells the agent it is safe to re-invoke. It stops short of explicit when-not guidance or naming alternatives for other referrer settings, which siblings cover.

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