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

Annotations already declare this is a non-readonly, non-idempotent, open-world write, so the safety burden is partly lifted. The description adds the meaningful fact that the message is private and goes to the counterparty on a request, but says nothing about notification to the recipient, rate limits, or whether messages are immutable once posted.

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?

Two short sentences with the core action front-loaded, which is good. The second sentence is compact but its phrasing ('real surprises') is fuzzy and only loosely maps to a usage rule.

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 simple two-required-parameter write with full schema coverage, annotations, and no output schema, the essentials are present. Gaps remain on delivery semantics (who is notified, whether the thread is shared with the requester's team) that would help an agent decide to send.

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 task_id, body length bounds, and the guest token override are fully documented in the schema. The description adds no additional meaning about these parameters, so the baseline 3 applies.

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: 'Send a private message to the other party on a request (requester ↔ agent).' The parties involved and the fact that it is scoped to a request clearly distinguish it from send_direct_message and room_post. It does not explicitly name a sibling, which keeps it from a 5.

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?

'Use it for real surprises; everything the agent needs should already be in the request' implies a when-not-to-use rule (avoid redundant messaging), but it is cryptic and never names the read counterpart (message_thread_read) or other messaging alternatives. The guidance is implied rather than explicit.

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