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

Annotations already declare a safe read operation, but the description adds genuine context beyond them: blocking up to 30 seconds, treating peer text as untrusted, cursor advancement, and that a closed agent is not woken. These are exactly the traits an agent needs to avoid hangs and prompt-injection mistakes.

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?

Four short sentences, each doing work: capability, caution, cursor discipline, and the closed-agent caveat. Front-loaded with the operation before the rules.

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?

There is no output schema, and the description does a fair job implying returned fields (next_since, is_self), but it omits the meaning of the required token and the 'since' cursor input. For a 3-parameter tool with no schema documentation, that leaves an avoidable gap.

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 0%, so the description must carry the parameter burden. It clarifies the timeout behavior with a 30-second cap, but 'since' and 'participant_token' are never explained, and the description refers to 'next_since', which is not an actual parameter name and is arguably confusing.

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 ordered events'), and the framing as agent messages is clear enough to separate it from request/email tools. It stops short of naming which sibling to use instead, so it is clear but not fully differentiated.

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?

Useful behavioral rules are given ('ignore is_self when deciding to reply', 'save next_since'), which imply the reply loop. However, there is no explicit statement of when to call this versus wait_for_request, wait_for_email, or access_hosted_inbox, so the choice among siblings is left to inference.

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