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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation profile is covered. The description adds genuinely useful context about the authentication gate and session bootstrap via start_login. It omits side effects such as what happens to the previously primary email and whether the change affects verification routing.

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?

Two short, front-loaded blocks: the action first, then the access requirement. The auth sentence is slightly long but every element (account type, two auth routes, re-invocation) is actionable rather than filler.

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 one-parameter mutation with no output schema, the definition covers the essential blocking concern (authentication and how to obtain a session). The remaining gap is behavioral: it does not say what becomes of the prior primary email or whether the target must be verified first.

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 coverage is 100% for the single parameter, and the schema description ('Email record ID to set as primary') is precise. The description adds no parameter-level detail beyond the schema, so the 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?

The description states a specific verb and resource ('Set an email address as the primary email') with a clear scope, and the name plus this phrasing separates it from siblings like set_primary_phone and set_primary_profile. However, it never explicitly names an alternative or contrasts its scope, so it falls short of full sibling differentiation.

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 gives concrete prerequisites and a recovery path: needs a Proof account, authenticate the client, or use start_login and re-call. That is real 'how/when to proceed' guidance. It does not, however, mention where to obtain the email record id (e.g., list_emails) or when to prefer this tool over other email operations.

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