list_sender_identities

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds useful provenance context ('as configured by the operator', 'not addresses taken from any message') that prevents the agent from confusing these with message-derived addresses. It stops short of mentioning ordering, pagination or empty-result behavior, though the output schema likely covers the shape.

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 tightly packed sentences: definition first, then sibling contract, then a disambiguating negative. No filler, and the most important information (what the addresses are) is front-loaded.

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?

An output schema exists, so return values need no prose explanation. For a no-arg, read-only enumeration tool, the description covers what is listed, who configures it, and how the values are consumed by sibling tools — everything an agent needs to call it correctly.

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 tool takes zero parameters, so the baseline is 4. The description adds nothing parameter-related, which is correct here — there is nothing to disambiguate — and it instead spends its words on the From-value contract.

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 and resource ('List the addresses this server may put in a draft's From header') and immediately defines their provenance ('as configured by the operator', 'the account's own addresses, not addresses taken from any message'). An agent can distinguish this from siblings like list_emails or list_folders without opening any 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?

Explicitly routes the agent to the siblings that consume these values: 'save_draft requires one of them as from; save_reply_draft and save_forward_draft accept one and pick a suitable address themselves when from is omitted.' This tells the agent both when the tool matters and when a from argument can be safely omitted.

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