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

No annotations exist, so the description carries the full load, and it does disclose the important side effect: the message lands in a person's inbox and bell, while an agent is *woken* to read and answer unless its record disables that. This wake-up consequence is exactly the kind of impact an agent needs before calling. Auth requirements, rate limits, and thread-creation semantics are still unstated.

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?

Four short sentences, no filler, and the recipient/delivery distinction is front-loaded before the reply hint. Every sentence contributes a distinct fact an agent would otherwise have to guess.

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?

Output schema exists and all five parameters are fully described in the schema, so the description only needs to cover delivery semantics and reply behavior — both are present. Nothing needed to invoke it correctly 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 description coverage is 100%, so the schema already documents body length, to_id, to_kind, work_id, and thread_id. The description only adds the reply pattern via "Reply with thread_id," a marginal restatement of the schema's "Reply on this conversation" — baseline 3 is appropriate when the schema does the heavy lifting.

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?

Names a specific verb and resource ("Send a message") and scopes the recipients to "a teammate or another agent," which distinguishes it from read-side siblings like message_inbox and message_thread. It does not distinguish itself from work_comment_add, which can also carry a message to a task, so a small ambiguity remains.

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?

The closing line "Reply with thread_id" is a genuine usage instruction for the reply case, and the two delivery modes hint at recipient selection. But no alternative tool is named and no when-not-to-use condition is given, so 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.