Message the other live agent sessions on this project (one-time note, not a brain card)

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

With no annotations provided, the description carries the full burden, and it delivers extensively: delivery is OS-user-local, machine-local, bounded by a 24h TTL, ephemeral, and replayable after reconnect. It also clarifies acknowledgment semantics (not proof of human reading), auto-consumption behavior, and failure receipts, which is far beyond typical disclosure.

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 long but densely packed with non-redundant behavioral details that matter for correct use. The front-loaded purpose sentence and examples make the primary intent immediately clear; the later lifecycle details are verbose but justified by the unusual ephemeral delivery semantics.

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 no annotations and no output schema, the description covers nearly everything an agent needs: recipient targeting, ephemerality, delivery constraints, expiration, receipt semantics, and the distinction from brain_note. The only minor gap is that it never explicitly describes the response/return shape, though it references a 'receipt line'.

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 100%, so the schema already documents all three parameters clearly. The description adds examples of message content and behavioral context, but it does not add new parameter-level meaning beyond what the schema provides. The baseline 3 is appropriate.

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 names a specific verb ('Leave'), a specific resource ('note for the OTHER active agent sessions'), and the intended scope ('working on this project right now'). It also differentiates itself from the durable brain_note tool by explicitly stating this is ephemeral and not persisted, which is the key distinction among sibling tools.

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 gives clear when-to-use guidance: leave a deliberate, targeted note for other live sessions. It explicitly contrasts with brain_note ('for a durable decision use brain_note instead'), and it describes the delivery conditions, such as requiring the peer to take a supported action. This is sufficient routing guidance for an agent.

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