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

Goes well beyond the annotations: discloses the per-call cap (50 newest), the VIP skip-when-batch rule, the VIP confirmation flow (in-app prompt or vipConfirmed:true), and that the result carries an undoId valid once for 7 days with counts to report. None of this is derivable from readOnlyHint/destructiveHint/idempotentHint.

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?

Purpose and the primary calling path are front-loaded, but the paragraph is dense and padded with material that belongs to a sibling tool: repeated 'archive' examples and a whole sentence about spam routing. Those sentences cost attention without clarifying how to unstar a message.

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 mutation tool with no output schema, it covers the essentials: how to target messages, VIP safeguards, confirmation gating, and what the response contains (counts, single-use undoId). Missing is any statement of what happens when a message is already unstarred (covered only indirectly by the idempotent annotation) and the examples remain mismatched to this tool.

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 67%; the description supplies the missing semantics for items (take inboxId+messageId from show_inbox's id block or structuredContent.rows), for sender (that sender's mail still in the inbox, up to 50 newest per call), and for vipConfirmed (only after explicit agreement, for a single VIP message). It largely duplicates the schema's own sender and vipConfirmed descriptions rather than adding new detail, hence not a 5.

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?

Opens with a specific verb+resource: 'Removes the star from the person's messages', which implicitly contrasts with sibling star_messages. However, the illustrative examples ('archive 2 and 5', 'archive everything from 2') name a different action than this tool, which muddies what the tool actually does.

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: use show_inbox ids for picked messages, sender{inboxId,email} for a sender's remaining inbox mail after review_unsubscribes, and spam goes through propose_mark_spam/confirm_mark_spam instead. It also states the autonomy rule ('work on your own only on a clear instruction or a saved agentRules rule; otherwise suggest and wait'). Slight deduction because the embedded examples reference 'archive', not unstarring.

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