inbox

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

With no annotations, the description does the disclosure work: it states the operation is non-mutating with respect to acknowledgement and that identity is auto-detected. It says nothing about return format, message ordering, pagination, or whether a cursor/limit exists — gaps that matter for a mailbox reader.

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?

Three short sentences with no filler, and the core operation is front-loaded. The closing sentence ("It identifies your own receiving session, not a peer filter") is slightly redundant with the sentence before it and with the schema text.

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 zero-required-param tool with no output schema this is nearly enough, but the description gives no sense of what the read returns or any limits on the result set. The ambiguity around what `sender` actually filters is addressed but the output side is not.

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% and the schema already explains `sender` is your own identity fallback, so the description largely restates it. The added conditional "omit sender when identity is detected" is mildly useful but does not go beyond the schema's meaning.

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?

"Read this session's external agentpeers mailbox" names a specific verb and resource, and the note that inspecting does not acknowledge implicitly separates it from the sibling `acknowledge` tool. It does not, however, contrast itself with `list_sessions` or `message_status`, so sibling differentiation is partial.

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 implies the workflow (read here, acknowledge separately) and gives one conditional rule for the `sender` param (omit when identity is detected). There is no explicit statement of when to call this versus `list_sessions`/`message_status`, so guidance is implied rather than stated.

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