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

With no annotations, the description carries the burden and does the important part: it flags the operation as a real send, discloses the connection-limit side effect, and imposes an approval precondition. It omits other behavioral facts an agent would want — idempotency, what happens if send_at is in the past, and whether the scheduled message can later be altered via reschedule_send or cancel_scheduled.

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 purpose and the 'THIS SENDS' warning before any argument detail, then a tight Args block. The trailing '### Responses: 200 Successful Response / Content-Type: application/json' is boilerplate that conveys nothing actionable and could be dropped.

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?

Given no annotations and no output schema, the description covers purpose, side effects, preconditions, and every parameter. The remaining gap is return behavior: with siblings like cancel_scheduled and reschedule_send, the agent would benefit from knowing whether a handle or job id comes back.

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 must compensate and it does: chat_handle is documented with its source tools (list_chats or search_chats), text is pinned to 'the exact message to send', and send_at is given accepted forms ('now', ISO-8601 with offset, or omit for immediate). All three parameters are meaningfully specified.

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 (send or schedule) and resource (a message into an existing conversation), plus the emphatic 'THIS SENDS' marker so the agent knows the operation's effect. The 'existing thread' framing implicitly separates it from the new-connection DM siblings without needing the schema.

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?

Gives a clear selection rule ('only when the user has approved this specific message') and a useful non-obvious fact — it creates no new connection and does not count against the daily connection limit. It does not, however, name the sibling alternatives (schedule_manual_dm, schedule_dm_to_person, draft_reply) that an agent should consider first.

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