List opencode subagents

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

Annotations only declare readOnlyHint=true; the description adds substantive behavioral context beyond that — the listing is scoped to the current server lifetime, and IDs survive restarts even when entries vanish. This restriction is exactly the kind of trait annotations cannot express.

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 sentences, front-loaded with what is returned and then the important persistence caveat. No filler, though the second sentence is slightly dense.

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?

No output schema exists, and the description describes the payload only loosely ('shows agents started or used'). Combined with an unexplained cwd parameter, a caller still lacks the details needed to interpret the result or pass the optional argument 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?

There is one parameter (cwd) with 0% schema description coverage, and the description never mentions it, so an agent cannot tell what cwd does or whether it is required. The description leaves the schema's gap unfilled.

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 states a specific verb+resource ('List this session's opencode subagents and the available agent types'), which rescues the generic name 'list' and makes the tool's intent unambiguous. It does not explicitly distinguish itself from a sibling list-type tool, but it clarifies its relationship to wait/send_message/stop.

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?

It gives clear context for when to use it (discovering started/used agents and available agent types) and a useful exclusion: agents from before a restart are not listed, but their agent_id still works with wait, send_message and stop. It stops short of naming an alternative tool for finding pre-restart agents.

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