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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safe-read profile is covered. The description adds genuinely useful output-shape context (inline [attachment: <filename> (<type>)] placeholders and the `attachments` array), but omits any mention of macOS permissions/Access requirements or result ordering, which matter for a tool reading a local message store.

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?

Two sentences, no filler, with the core read action front-loaded before the attachment-format detail. The second sentence is dense but every element (placeholder syntax, position in text, attachments array fields) carries information an agent needs to parse the result.

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, the description need not explain return values, yet it still clarifies how attachments appear inline; with annotations covering the safety profile and all three parameters documented in the schema, the definition is nearly self-sufficient. The remaining gap is operational context such as permission requirements or default message ordering.

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 100%, so limit, chat_id and contact_name are already fully documented in the schema, including that contact_name is an alternative to chat_id. The description restates the same chat_id/contact_name axis without adding format or precedence detail, so baseline 3 is appropriate.

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 ("Reads messages from an iMessage conversation") and pins the lookup key as "chat ID or contact name", which distinguishes it from the platform-scoped read_messages siblings (telegram_read_messages, signal_read_messages, etc.). It never names search_messages or list_message_chats directly, so sibling differentiation is implicit rather than explicit.

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 phrase "by chat ID or contact name" implies the two supported entry points, and the schema points chat_id back to list_message_chats, but the description gives no when-to-use versus search_messages (keyword lookup) or list_message_chats (discovery). Usage must be inferred from the platform scoping and parameter names.

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