Apple Mail MCP Server

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

With no annotations provided, the description carries the full burden and discloses important behavioral traits: the precedence of message_ids over filters, the safety limit of max_updates (default 10), and the apply_to_all guardrail requirement. It also describes the return value. It does not mention error handling behavior or idempotency characteristics.

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?

The description follows a logical docstring structure with purpose upfront, followed by behavioral logic, then detailed Args, and finally Returns. It is appropriately sized for the complexity (10 parameters with zero schema documentation), though the Args section contains some repetitive 'Optional' qualifiers that could be tightened.

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 10 parameters, no annotations, and zero schema coverage, the description successfully documents all inputs and the filtering logic. The mention of output schema existence satisfies return value needs. Minor gaps remain regarding error scenarios (e.g., invalid message_ids) and atomicity guarantees.

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?

Given 0% schema description coverage, the Args section comprehensively compensates by documenting all 10 parameters with semantics, examples (e.g., 'Gmail', 'Work' for account), and valid values (e.g., 'mark_read', 'flag' for action), adding essential meaning absent from the structured 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?

The opening sentence clearly states the specific action (update email status) and the exact operations supported (mark as read/unread or flag/unflag), distinguishing it from sibling tools like compose_email or move_email which handle different email operations.

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?

The description provides clear internal logic for when to use message_ids (exact ID matching that ignores other filters) versus when to use filtering parameters (subject, sender, age). However, it does not explicitly contrast with sibling alternatives to guide selection between this and tools like manage_trash or move_email.

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