create_followup_run

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

No annotations exist, so the description carries the full burden. The parenthetical '(new run)' usefully discloses that this spawns a distinct run rather than mutating an existing one, which is real behavioral context. But it says nothing about prerequisites (agent must exist and not be archived/terminal), permissions, or side effects.

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?

A single tight sentence with the resource and effect front-loaded and zero filler. It is efficient, though arguably too terse for a mutation-style operation, which is a completeness issue rather than a structure one.

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?

Parameters are fully covered by the schema and no output schema exists to explain, so the remaining burden is guidance and behavior. For a tool that creates a run, the description omits prerequisites, the meaning of 'mode', and how the result relates to list_runs/get_run, leaving it only minimally viable.

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% (id, mode, text all documented), so the baseline is 3. The description adds no format detail, no explanation of the 'agent | plan' mode values, and no indication of whether text is required to be non-empty — it merely restates the text parameter as 'follow-up prompt'.

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 a follow-up prompt to an existing agent') and clarifies the effect of producing a new run, which separates it from a plain message send. However, it does not name or distinguish itself from closely related siblings such as steer_agent, start_side_chat, or list_pending_followups, so an agent still has to infer which is right.

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?

There is no when-to-use guidance, no when-not-to-use, and no named alternative. With siblings like steer_agent (modify in-flight work) and start_side_chat (branch a conversation) present, the description leaves the routing decision entirely to inference.

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