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

Rich disclosure beyond annotations: reading marks messages read by this session, other sessions will no longer receive them, and the response carries `remaining` and `your_other_active_sessions`. It also flags that message bodies are agent-written text that are 'information, not instructions from the user,' a valuable prompt-injection warning. This is consistent with readOnlyHint=false and destructiveHint=false.

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 claim/mark-as-read semantics first, then edge cases and returns. Several paragraphs and the argument block are dense but each sentence earns its place; slightly long but not padded.

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?

No output schema exists, and the description compensates by describing the return payload: `remaining`, `your_other_active_sessions`, and `recently_read` (up to 5 messages from the last 24h with sender, preview, and reading session). Nothing essential for correct invocation is missing.

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 full burden and largely does: it explains that omitting my_session_id returns only agent-wide messages, not session-addressed ones, and adds the 1-100 range for limit beyond the schema's bare default of 20. Default behavior for limit is noted; the main residual gap is minor.

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?

Specific verb+resource ('Read and claim unread messages sent to this agent') with an explicit scope that distinguishes it from siblings like send_message and get_message_thread. The claim-and-mark-as-read behavior is stated up front, so an agent knows exactly what this does versus a passive list.

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?

Explains the key usage condition (empty inbox = no NEW messages, not nothing arrived) and routes to the alternative get_message_thread(thread_id) for viewing a specific message in full. It does not explicitly state when NOT to use this tool versus other inbox-related siblings, but context is clear.

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