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

With no annotations present, the description carries the full burden, and it delivers substantial disclosure: blocking behavior ('The call blocks until the agent finishes'), automatic backgrounding, the run_in_background escape hatch, worktree isolation semantics including cleanup ('removed if unchanged'), and the no-conversation-context behavior. These are exactly the non-obvious behavioral traits an agent needs and are not derivable from the schema.

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?

Every sentence earns its place and the content is dense with no filler, but it is a single run-on paragraph that is hard to scan. The size is arguably justified by the tool's complexity, yet the lack of structure (no bullets, no separation of behavior vs parameters) makes it harder to parse than it should be.

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 13-parameter tool with no annotations and no output schema, the description covers the most critical non-obvious behaviors (blocking, backgrounding, isolation cleanup, subagent resolution, context isolation). It could add a bit on permission_mode behavior or how the final result is returned, but given the complexity, the coverage is close to complete.

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?

At 69% schema coverage, the description meaningfully compensates for the schema on the hardest parameters: it explains what subagent_type accepts (Claude .claude/agents/ definitions vs opencode agents, with their prompt/tools/permissionMode/maxTurns applying), what isolation 'worktree' induces, and the run_in_background blocking trade-off. Some params (output_schema, max_turns, effort, tools) are left to the schema, but the description targets the most complex ones.

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?

Opens with a specific verb+resource ('Launch a subagent that runs on an opencode model'), states the scope ('in the current project') and immediately distinguishes itself from siblings by invoking the built-in Agent tool it mirrors. The sibling set (send_message, wait, stop, list) is clearly different, so there is little chance of confusing this tool with an alternative.

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?

Provides clear contextual guidance: instructs to 'give a self-contained task prompt' and explains that the agent 'starts with no conversation context and returns only its final report', which tells an agent when this tool is appropriate (standalone tasks) and what to expect. It references the built-in Agent tool as a mirror but stops short of explicit when-not-to-use or exclusion statements, which would push it to a 5.

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

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.

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

With no annotations provided, the description carries the full burden and does disclose meaningful behavior: the subagent resumes with its full prior history, its worktree is preserved if one was kept, and the call returns a new final report. It also discloses cross-restart persistence, a real operational trait. It omits what max_turns does by default or that run_in_background makes the call async.

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 sentences, zero filler, with the core verb and the agent_id anchor front-loaded. The trailing restart sentence is a worthwhile edge case rather than padding, though it could be tightened.

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 stateful, mutating tool with no annotations and no output schema, the description does tell the agent what comes back ("its new final report") and how state is restored. What's missing is the behavior of the two optional control parameters (max_turns, run_in_background), which materially change how the call behaves.

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 0% across 4 parameters, so the description must compensate. It clarifies `agent_id` semantics (finished agents, agents from before a restart) but says nothing about `max_turns` or `run_in_background`, leaving half the parameters entirely unexplained anywhere.

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 and resource ("Send a follow-up message to a finished opencode subagent by agent_id") and immediately distinguishes itself from siblings like `agent` (which starts a new one) and `stop`/`wait`. An agent can tell exactly what this does without opening the schema.

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 scopes usage clearly (a *finished* subagent) and adds a valuable edge case: agent_ids that predate an MCP/Claude Code restart or that were interrupted by one. However, it never explicitly names alternatives or states when *not* to use it (e.g., use `agent` for a fresh subagent, `stop` to cancel).

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

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

No annotations are present, so the description carries the behavioral burden and does add real value: it says the call returns partial output produced so far and that IDs survive an MCP server restart. It does not state whether the abort is irreversible, whether it errors on finished agents, or any permission requirements, leaving gaps for a mutation-style tool.

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, front-loaded with the action, then the return behavior, then the edge-case note. Nothing is padded; it is appropriately sized for a one-parameter tool.

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?

With no annotations and no output schema, the description covers the core action, the partial-result return, and the restart edge case. It still omits idempotency, failure modes when the agent is already stopped, and error semantics — meaningful gaps for a termination operation.

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% and agent_id is undocumented in the schema, but the description adds genuine meaning about it — that IDs minted before a server restart remain valid. That is one useful semantic detail, though it does not fully document format or validity expectations for the single parameter.

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 (abort) and resource (running opencode subagent), and clarifies it stops an in-flight subagent rather than waiting on or messaging one. It stops short of explicitly naming which sibling to use instead, so it is clear but not sibling-routing.

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 phrase 'running opencode subagent' implies the condition for use, but no alternative is named (e.g., when to use stop vs wait), and there is no guidance on what to do if the agent is not running or has already finished.

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

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

No annotations are provided, so the description carries the full burden. It usefully discloses a non-obvious behavioral trait — agent_ids survive an MCP server restart — but omits blocking/polling semantics, what happens when the agent never finishes or the id is invalid, and whether early timeout returns partial state.

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 tightly-written sentences with zero padding; the core purpose is front-loaded and the restart caveat is a single qualifying clause rather than a paragraph. Every sentence 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 simple wait tool with no output schema and only two parameters, the definition covers the essential purpose and one non-obvious behavior. The remaining gap — error/failure and timeout-result semantics — is meaningful but small given the schema already explains early return.

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?

With two parameters and 50% schema coverage, timeout_seconds is already documented in the schema as an early-return mechanism. The description references agent_ids but adds no format, provenance, or semantics for agent_id beyond what the parameter name implies, so it neither compensates nor regresses.

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 ('Wait for a background opencode subagent and return its result'), which an agent can immediately distinguish from siblings like send_message, stop, list, and agent. The scope is unambiguous and the outcome (returns the result) is stated.

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?

Usage is only implied: 'background' subagent suggests it is used when polling an asynchronously-started agent, but no explicit when-to-use, when-not-to-use, or alternative (e.g., vs. list or agent) is named. No exclusions or prerequisites are given.

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