create-focused-inbox-override

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

Annotations already mark this as destructive (destructiveHint: true) and openWorldHint: true. The description adds behavioral context beyond that: it explains the upsert behavior ('If an override already exists for that SMTP address, POST updates the existing override's name and classifyAs') and clarifies that classifyAs must be 'focused' or 'other'. No contradiction with annotations, and the added context is valuable for correct invocation.

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?

The description is reasonably concise and front-loaded with the main purpose. It includes a practical tip and important constraints (e.g., do not invent addresses). While it's slightly longer than necessary, each part adds value and the structure (description followed by tip) aids readability.

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?

Given the nested body schema, the upsert behavior, and the need for address resolution, the description is complete. It covers the body format, permissible classifyAs values, behavior on existing overrides, and how to obtain a valid sender address. There is no output schema, but the description doesn't need to explain return values; the essential operational details are all present.

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?

The schema covers 75% of parameters, and the description enriches meaning by providing a concrete body example ({ classifyAs: 'focused', senderEmailAddress: { name: 'Display Name', address: 'sender@example.com' } }) and stating that classifyAs must be one of two values. It also emphasizes resolving the sender's address reliably, which is a key semantic point beyond the schema's field descriptions.

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 clearly states the tool's action: 'Create an override for a sender identified by an SMTP address' and the effect ('Future messages from that SMTP address will be consistently classified'). It is specific about the resource (Focused Inbox override) and distinguishes it implicitly from sibling tools like update-focused-inbox-override and delete-focused-inbox-override by describing the create/upsert behavior.

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?

The description provides clear context on when to use this tool: it creates an override and, if one already exists, it updates it (useful for renaming a sender). It also advises resolving the sender's address using list-users or reading a mail header, and explicitly says 'do not invent SMTP addresses'. However, it does not explicitly contrast with the sibling update-focused-inbox-override, so it lacks a direct 'when not to use this' exclusion.

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