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 of behavioral disclosure. It successfully explains the UI behavior of the 'open' action and notes that output is formatted by action type. However, it fails to disclose that 'delete' and 'send' actions are destructive/irreversible, which is critical safety information for an agent.

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 docstring format with explicit 'Args' and 'Returns' sections is appropriate and scannable. While not terse, the detail is justified by the complete absence of schema descriptions; every sentence provides necessary constraint information or behavioral context without redundancy.

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 complex multi-action tool with eight parameters, the description adequately covers input requirements and conditional validation rules. It acknowledges the existence of formatted output (confirmed by output schema presence), though it could briefly mention error handling or the specific nature of the formatted returns.

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 description comprehensively compensates by documenting all 8 parameters. It provides crucial conditional logic (e.g., subject/body required for 'create', draft_subject required for 'send/open/delete'), format hints (comma-separated emails), and concrete examples ('Gmail', 'Work') that the schema completely 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 description clearly states the tool manages draft emails and enumerates the five supported actions (list, create, send, open, delete). However, it does not explicitly differentiate this tool from siblings like 'compose_email' or 'create_rich_email_draft', leaving ambiguity about which tool to use for simple draft creation.

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 provides specific guidance for the 'open' action (opens a visible compose window for review), which is helpful. However, it lacks broader guidance on when to use this multi-purpose tool versus specialized siblings, and does not mention prerequisites like authentication or existing account requirements.

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