opencode_retry

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description states the tool loads a checkpoint and spawns a new session, which covers the basic mechanism, but doesn't disclose side effects (e.g., does the new session supersede the current one? Is the current session killed? What happens to in-flight work?), error conditions (invalid checkpoint_id), or any state implications.

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?

Single sentence, zero waste. Every word earns its place. Front-loads the core action clearly.

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 there is no output schema and no annotations, the description must carry more weight. For a tool with two parameters including an optional continuation_hint, the description could explain how the hint combines with the original session instructions, whether the retry replays prior conversation or starts fresh from the checkpoint state, and what the return value indicates. This is a moderately complex state-management operation that leaves significant behavioral questions unanswered.

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%, so both parameters are described in the schema (checkpoint_id is the ID to retry from; continuation_hint is an optional extra instruction). The description adds that it's a 'retry' operation and mentions 'continuing from that state', which adds marginal context about the continuation_hint parameter being an addition to the original instruction. However, it doesn't elaborate on the format or semantics of continuation_hint beyond the schema.

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 uses a specific verb ('Loads') with a clear resource ('saved checkpoint') and action ('spawns a new session continuing from that state'). It clearly distinguishes from siblings like opencode_checkpoint (which saves) and opencode_list_checkpoints (which lists). However, it doesn't explicitly differentiate from opencode_start or opencode_switch, which might also involve session initiation.

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 implies usage (load a checkpoint to continue work), giving some context. However, it doesn't explicitly state when to use this vs alternatives, doesn't note prerequisites (e.g., checkpoint must exist), and doesn't clarify when NOT to use it (e.g., if you want a fresh session).

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