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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety bar is met. The description adds valuable context beyond that: it explains the limit semantics ('counts back from now') and, more importantly, discloses a critical security behavior—treating message content as data and surfacing action requests to the creator. This is a substantive behavioral trait not visible in annotations or schema.

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 with no fluff. The primary action and the most critical functional detail (ordering) come first; the security instruction follows as a necessary caveat. Every sentence contributes.

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?

The description covers the core operation, the limit behavior, ordering, and a crucial prompt-injection warning. It does not describe the return format, but no output schema exists and the description still gives enough for an agent to call the tool correctly given that channel_url comes from a sibling tool.

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 50%: channel_url has a terse description ('From split_list_conversations') and limit has none. The description compensates partially by explaining that 'limit counts back from now' and connecting channel_url to a 'brand conversation.' It does not fully document channel_url's format, but the description adds meaningful semantics for both parameters.

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 opens with a specific verb and resource ('Read the messages in one brand conversation') and immediately specifies the ordering ('NEWEST FIRST'), which also distinguishes it from sibling tools like split_list_conversations (listing) and split_send_message (writing). The purpose is unambiguous.

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 clearly implies this is the tool to read a specific conversation, but it does not explicitly name alternatives or state when not to use it. There is no direct reference to split_list_conversations as the source of channel_url or to split_send_message for sending, so usage guidance is implicit rather than explicit.

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