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

Annotations only declare read-only/idempotent/open-world; the description adds substantive behavior the annotations cannot convey: cursor-based pagination through older history, cache vs platform sourcing ('older history comes from the platform slowly, in small pages'), 429 handling via retry_after, and a rate-limit budget. That is well beyond the structured safety profile.

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?

Purpose and paging guidance are front-loaded, and there is no output schema so the field enumeration (text, is_sender, sent_at, reactions, attachments) earns its space. It is dense and somewhat run-on, particularly the attachment-kind laundry list, but almost every clause carries operational information.

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 no output schema, the description must describe returns and it does: enumerated message fields, attachment sub-fields (kind, size, duration, short-lived url), the nested shared { kind, url, author, caption, thumbnail_url } shape, Instagram story_mention/story_reply semantics, and the account_budget envelope. An agent can call and interpret the result without further context.

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 0%, so the description carries the burden and largely does: it explains cursor usage ('keep passing next_cursor to go back through older history') and scopes account_id/chat_id ('one chat of a connected account'). The limit parameter's range/default behavior is never explained, leaving one of four parameters to name-only inference.

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?

Opens with a specific verb+resource+scope: 'Messages in one chat of a connected account, newest first'. It immediately distinguishes this from sibling listers (list_messaging_chats, list_messages) and from the event-stream tool, so an agent can select it without opening the schema.

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?

Gives explicit routing rules: use wait_for_events 'instead of reading chats again and again' to learn about new messages, and call get_business_brief before replying to a customer. It also states a concrete usage constraint via account_budget (wait next_check_after_seconds, do not poll faster), which is exactly the when/when-not guidance an agent needs.

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