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

Annotations cover the safety profile (readOnlyHint=true, destructiveHint=false), so the bar is lower, yet the description goes well beyond: without account= on multi-account machines it returns the account list instead of scanning, scanning all accounts has no time limit and can block Mail for other requests (#2268), and exactly 1 account is unaffected. That is substantive behavioral disclosure an agent cannot get from structured fields.

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?

Front-loaded with the primary purpose, then an IMPORTANT block for the highest-risk gotcha, then pagination. Every sentence carries weight, though the pagination paragraph partly restates what the limit/offset schema descriptions already say, so it is slightly longer than strictly necessary.

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 not be described. The description covers routing to alternatives, the multi-account failure mode, and paging limits — everything an agent needs to invoke this correctly, with no meaningful gap remaining.

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 100%, so baseline is 3, but the description adds real meaning: the rationale and consequence of the account parameter (fallback to returning the account list, blocking behavior), and concrete pagination usage ('offset=20 for page 2 with limit=20') plus the hard cap rationale. The account-perf note partially duplicates the schema text, which keeps it from 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?

States a specific verb and resource ('Lists email headers (subject, sender, date, unread)') scoped to Apple Mail on this Mac, and explicitly names what it is not: it points to read_email for bodies and m365_list_emails for Microsoft 365 mailboxes outside Mail.app. An agent can distinguish it from the many sibling email/search tools 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?

Gives an explicit trigger ('when the user wants to see or triage their inbox on this Mac'), names the read_email alternative for full bodies, and routes the non-Mail.app M365 case to m365_list_emails. It also states a hard operational condition: on 2+ account machines, call with account=<name> from list_email_accounts.

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