agent_control

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

With no annotations, the description carries the full burden. It usefully discloses the API mechanism and the error behavior with CLI fallback instructions. However, it says nothing about the disruptive consequences of abort/reset/compact (e.g., potential context or state loss) or any prerequisites/auth requirements, which is significant for a tool that mutates running sessions.

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 tight sentences with the purpose and action list front-loaded, followed by error behavior. The clause 'Uses the gateway /tools/invoke API' is an implementation detail that adds little for an agent deciding to call the tool, but the rest is efficient and earns its place.

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?

For a 3-param tool with no annotations and no output schema, the description covers action semantics, conditional parameter requirements (via schema), and error/fallback behavior. It stops short of stating per-action side effects or the response format, but an agent has enough to decide whether and how to invoke it 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 100%, so the baseline is 3 and the schema already documents the action enum and the message requirement for steer. The description adds marginal semantic color ('abort stuck agents', 'compact their context'), but does not materially exceed what structured fields provide.

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 ('Control') + resource ('running agent sessions') and enumerates four concrete actions: abort, steer, compact, reset. This distinguishes it from siblings like agent_dispatch (starting agents) and agent_query (inspecting agents) without needing to open their schemas.

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?

'Running agent sessions' implies the tool applies to already-dispatched agents, and the action list hints at when each is appropriate (e.g., abort for stuck agents). However, the description never explicitly contrasts it with agent_dispatch or agent_query, nor states when not to use it; routing is left to inference.

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