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

Annotations already declare read-only, idempotent, non-destructive, open-world, so safety is covered; the description goes beyond by disclosing serial fetching to respect provider rate limits, partial-failure semantics via { messages, missing }, body truncation signalling with bodyTruncated, and a junkHint that moved nothing. The one gap is that it doesn't say what auth or permission is required per provider, and some of the length is spend on return shape rather than behavior.

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 scope are front-loaded and every sentence carries operational content, but the whole thing is one long run-on paragraph mixing purpose, batching, body, links, unsubscribe, and junk hints. It would scan faster split into short labeled lines; still, there is little wasted wording.

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?

There is no output schema, and the description covers the return contract in detail: message shape, bodyUntrusted, bodyTruncated, links with text/full URL/mismatch, unsubscribe fields, and junkHint structure. An agent can act on the response, including the untrusted-data rule, without further documentation.

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% and the schema already explains messageId ("Omit when passing messageIds") and messageIds ("1 to 10 message ids"). The description confirms the 1-10 cap and adds that ids are fetched sequentially with per-id failure isolation, which is real added meaning, but it does not clarify inboxId at all, so it stops short of compensating for the coverage gap.

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?

Specific verb and resource ("Returns one message with its full body, or up to 10 with messageIds") plus explicit scope ("Works with any connected inbox: Gmail/Google Workspace, Outlook/Microsoft 365, iCloud, or IMAP"). It also carves out the boundary against three named siblings that only carry a preview, so the agent can choose without opening schemas.

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?

States exactly when to call this instead of alternatives ("list_messages, search_mailbox, and show_inbox only carry a short preview; call this for the body") and gives explicit conditions for the batch path (1-10 ids, fetched in turn). It also gives a decision rule for junkHint ("ask the person before acting on it"), which is when-not guidance.

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