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

Adds real behavior beyond the annotations: verification semantics ('a message counts as marked only when a second read shows the new state'), the Mail.ReadWrite permission requirement, and the consent_required failure mode for older connections. The 'nothing is sent, moved or deleted, so it asks for no confirmation' claim sits in mild tension with destructiveHint=true, but does not directly contradict it since the hint concerns state mutation generally.

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-loads the trigger condition and keeps every clause load-bearing (purpose, parameters, verification, permission, alternative). It is dense—one long compound sentence carries most of the content—but nothing is wasted.

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 format need not be explained; the description instead covers the permission prerequisite, the consent recovery path, the verification requirement, and the platform alternative. Nothing an agent needs to call this correctly is missing.

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 the baseline is 3; the description still adds value by bounding message_ids to 20, identifying message_id as the single-message form, and framing unread=true as 'mark as unread'. The account parameter's resolution order is left to the schema.

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+resource ('emails of their Microsoft 365 / Outlook account marked as read, or as unread') and names the sibling it is not ('For mail in the Mac's Mail app, use mark_email_read'). An agent can distinguish it from mark_email_read and flag_email 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 both usage directions (mark read vs unread=true to 'come back to a message later'), specifies the ID sources (m365_list_emails, m365_search_emails, m365_read_email), and names the explicit alternative for Mac Mail. Exclusions and routing are both covered.

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