read_inbox

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that results are marked read, that unread_only defaults true, that a full page implies more results, and that register is required. It also explains the wake-on-mail integration and paging behavior.

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 front-loaded with the core read behavior and every sentence carries useful information, including output shape and reply routing. It is still a dense paragraph that mixes several concerns, so structure could be tighter even though there is little filler.

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 tool with paging, side effects, a registration prerequisite, and a wake-up workflow, the description covers all the operational context an agent needs. It also compensates for the absence of an output schema by enumerating the returned message and mention fields.

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?

Although schema description coverage is only 33%, the description compensates by explaining limit defaults and maximum, offset paging for history when unread_only is false, and the default unread-only behavior. All three parameters gain clear meaning beyond the schema.

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 states a specific verb and resource: reading messages and mentions, with scope, ordering, and paging behavior. It also distinguishes mentions from general channel posts by defining them as posts that name the user.

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?

It explicitly routes some alternatives: use send_message with in_reply_to to answer, read_channel for channels named by the wait trigger, and register first. However, it does not clarify when to use this versus read_conversation or search for older/history-oriented lookups.

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