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

With no annotations, the description carries the full behavioral burden. It discloses ordering ('last written first') and return fields ('recipients, subject, text and files'), which are useful traits beyond the name. It does not mention pagination or limits, so it is strong but not fully complete.

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 sentences, both front-loaded and purposeful. The first states scope, ordering, and return contents; the second handles sibling differentiation, with no wasted text.

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 list tool with no output schema and no annotations, the description does well: it states what is returned and in what order, and distinguishes it from list_drafts. It omits pagination or volume behavior, which is a remaining gap given the absence of structured annotation help.

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 single optional address parameter is fully documented in the schema, including that it comes from list_sender_addresses. The description does not add parameter-specific meaning 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 uses a specific verb-resource pair ('Lists the messages begun... and never sent') and adds precise scope: account addresses, unsent, last-written-first. It explicitly distinguishes this from the sibling list_drafts, so an agent can tell which list tool to choose.

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 explicitly names the alternative, list_drafts, and explains the difference: 'unsent texts, not the answers Iris wrote for review.' That is a direct when-to-use-this-vs-sibling cue, leaving little inference for an agent.

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