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

With no annotations, the description carries the full behavioral burden. It discloses the three-follow-up limit, 'no automatic nagging,' fail-closed behavior on a changed room, and when to stop. It does not mention permissions or success/failure response details, so it is strong but not exhaustive.

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 with no wasted words. The action is front-loaded, and each sentence contributes a distinct constraint or behavior. This is an appropriately sized, well-structured description.

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 the key preconditions, limits, failure mode, and stopping rules needed to invoke the tool correctly. It omits return/error shape and permission requirements, but these are less critical for selection and invocation than the behavioral constraints it does state.

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 high at 80%, so the description does not need to compensate much. It adds modest value by clarifying that revision must be current and by mapping the retry key to idempotency_key, but text and request_id semantics are already clear from the schema. This is adequate, not exceptional.

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?

The description opens with a specific verb and resource: 'Send a justified follow-up in this request's existing room.' This clearly identifies the operation and distinguishes it from sibling tools like message_send or request_retry by anchoring it to the request's existing room. The purpose is unambiguous.

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 description provides explicit preconditions ('Requires current revision, exact original audience, and a retry key'), stop conditions ('stop when blocked, cancelled or no longer useful'), and instructs the agent to read history first. It does not name alternative sibling tools, but the context is clear enough to guide correct usage.

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