Read inbox

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

With no annotations supplied, the description carries the full burden and does so thoroughly: reading marks messages read 'for every agent on the account', paging with `before` never marks anything, and read receipts are sent on WhatsApp by default with per-number settings and an explicit opt-out. It also explains what the response contains (media, reactions, new_since_last_read, new/new_reactions flags), which an agent cannot infer from structured fields.

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?

Front-loaded with the core action and ordering, and nearly every clause carries non-obvious information. It is a single dense block with heavy parentheticals and em-dash asides, and the read-receipt opt-out is restated in both the description and the schema, which slightly harms scannability.

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 7-parameter, side-effecting read tool with no annotations and no output schema, the description covers both the inputs' interaction and the shape of the returned data (account, media, reactions, new flags, new_reactions). An agent has enough to invoke it correctly and to anticipate the read-state and receipt side effects.

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%, so baseline is 3, but the description adds cross-parameter meaning the schema does not: how `before` interacts with mark_read (paging never marks), and how mark_read:false interacts with read_receipts (none sent unless read_receipts is true). The remaining parameters (limit, channel, connection_id, chat_id) are left essentially to the schema, which documents them well.

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 ('Read recent messages across all your connected accounts, newest first') plus the ordering and per-message account attribution. It is clearly distinguishable from siblings like list_chats (which supplies chat_id), get_media (for media payloads), and search, none of which read a chronological inbox.

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 concrete routing: filter by channel/connection/chat, 'chat_id from list_chats', page back with `before`, and 'call get_media to see it' when a message has media. It also explains the mark_read:false path for a non-mutating look. The one gap is that it never contrasts itself with the sibling `search` tool for finding older or specific content rather than paging the inbox.

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