update_mail_status

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

Annotations declare destructiveHint=true, and the description goes well beyond that: it explains that only two booleans change, that nothing is destroyed, that re-issuing the opposite value is the undo, that it skips the backup plane move_mail uses, that messages are re-read so `results` reflect what actually persisted, and that Automation access is required. That is unusually rich disclosure of write semantics and failure/verification behaviour.

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 is front-loaded and almost every sentence adds actionable information. The middle paragraph is dense and chains multiple facts per sentence, which makes it harder to scan than a short bulleted structure, but there is no filler to cut.

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?

The tool is a batch mutation with 6 parameters, an output schema and annotations; the description covers id format, batching limit, the mailbox disambiguation trade-off, the required-field invariant, colour semantics, undo story, persistence verification and permissions. An agent has everything needed 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?

Schema description coverage is 0%, so the description must carry all meaning and it does: `ids` is RFC822 message-ids from a prior read, comma-separated, max 25; `mailbox` is an opaque imap://<uuid>/<path> token taken verbatim; `flag_color` enumerates the allowed names and implies flagged; `dry_run` defaults to false. Every parameter is given semantics the bare schema lacks.

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 first clause names a specific verb pair and resource: 'Mark Mail messages read/unread and flag/unflag them.' The scope (status booleans + optional flag colour) is distinct from siblings like move_mail, trash_mail and mail_search, so an agent can route without opening the 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?

It states exactly when to pass `mailbox` (copy the `folder` token verbatim from the same read) versus when to omit it (each id resolved through Mail's index, allowing a multi-mailbox batch). It also gives the precondition 'at least one of read, flagged or flag_color is required' and explicitly contrasts itself with move_mail's backup plane.

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