send_message

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

No annotations, so the description carries the full burden. It usefully discloses async delivery semantics ('delivered on their next Tower contact') and the task/reply protocol, but says nothing about auth, failure behavior for unknown agents, rate limits on broadcast, or delivery guarantees.

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 dense sentences that front-load the core action and broadcast capability, then the delegation/reply protocol. No filler, though the second sentence packs two ideas together.

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?

An output schema exists, so return values need no explanation, and the async-delivery model is conveyed. But with 9 parameters, 0% schema coverage, and no annotations, several parameters and behaviors remain undocumented for an agent to call this correctly.

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% across 9 parameters, so the description must compensate. It clarifies toAgentId (including '*'), the kind enum, and replyTo, but leaves body, repo, fromAgentId, size, repoId, and projectId entirely unexplained, covering only about a third of the surface.

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+resource ('send an async message or task to another agent') and clarifies the '@*' broadcast target. The send/receive split from sibling fetch_messages is inferable, but no sibling is named explicitly, so it falls short of 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?

Explains how to use the tool's modes: kind 'task' delegates work and should be answered with kind 'task_update' (replyTo=task id). This gives clear in-tool usage guidance, though it does not contrast with sibling tools like accept_task/complete_task.

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