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

Annotations already declare read-only and non-destructive, so the bar is lower. The description adds meaningful behavioral context: it includes nested subfolders, covers various account types, warns about slow performance when scanning all accounts on macOS 15+, and explains the source of message counts (local index vs live count) plus the unread_count_note in the response. No contradiction with annotations.

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 is information-dense with no filler, but it runs longer than necessary because it covers multiple caveats and exceptions. Each sentence earns its place, though some aggregation could tighten it. Still well-structured, purpose is front-loaded.

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?

With an output schema present and annotations covering safety, the description covers all necessary invocation details: account provenance, default behavior, performance warnings, and count semantics. Nothing an agent needs to call it 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% for both parameters, but the description adds significant semantics beyond the schema: account must come from list_email_accounts and defaults to all accounts; include_counts has performance tradeoffs, defaults to off, and includes nuance about where counts come from. This enrichment justifies a top score.

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 the full folder tree for Apple Mail accounts, including nested subfolders. It explicitly names the sibling tools that depend on its output (move_email, list_emails) and distinguishes itself from m365_list_emails for Graph-only mailboxes. Clear differentiation.

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?

Provides explicit when-to-use guidance ('Use this to discover exact folder names...') and when-not-to-use (Graph-only mailbox → use m365_list_emails instead). It also gives operational tips, such as passing account=<name> to avoid slow full walks and include_counts=true when counts are needed. This goes beyond implied usage.

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