team_time_reply_agent_message

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

Annotations already declare destructive=true, non-idempotent, openWorld, so the bar is lower; the description still adds real behavior — late replies remain labeled late, and replies may not target reply messages or stand in for another run. It doesn't explain why the call is destructive (whether it consumes/closes the message) or who can see the reply, which keeps it from a 5.

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?

Three short sentences, purpose first, then the two hard constraints. No filler and nothing buried.

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?

Covers purpose and key guardrails but leaves ambiguity for a destructive, state-changing messaging tool with no output schema: what happens to the original message, what "late" means operationally, and what a successful reply returns are all unstated.

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 carry parameter meaning; it implies runId is the addressed run and messageId is the question/note being answered, but never states UUID formats, body limits (2000 chars), or that all three are required.

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 (reply) and resource (a task question/note), and pins the actor to "the addressed run". It is distinguishable from siblings such as team_time_leave_agent_message or team_time_ask_agent, though the term "addressed run" is domain jargon left undefined.

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 explicit when-not guidance: "Never reply to reply messages or impersonate an old run." However it never names the alternative tool for those cases (e.g., leave_agent_message or ask_agent), so the routing decision is only half-specified.

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