opencode_read

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 discloses what it returns (last 200 lines + status) which adds basic behavioral context. However, it doesn't disclose whether output is cleared after reading, whether this is destructive, or the exact nature of 'session status'. For a read tool the disclosure is adequate but not rich.

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, front-loaded with the key action and output. Zero waste. Could add a bit more context but it's efficiently written and to the point.

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 single-parameter read tool with no output schema, the description covers the essentials: what it returns and the scope (last 200 lines + status). However, it lacks context on when to use it vs. opencode_logs or opencode_context, and doesn't explain what 'session status' contains. Adequate but with gaps given the large sibling set.

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%—the single optional session_id parameter is documented in the schema. The description adds nothing beyond the schema for this parameter. Baseline 3 is appropriate since the schema fully documents the 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?

The description clearly states the verb (returns) and resource (last 200 lines of buffered output plus session status). It distinguishes this from siblings like opencode_logs (which likely fetches full logs) and opencode_status (status-only). Clear enough to communicate the core function, though it doesn't explicitly differentiate from all siblings.

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 context—reading buffered output from a session—but doesn't explicitly state when to prefer this over siblings like opencode_logs, opencode_status, or opencode_context. No when/when-not guidance or alternative tool references. The default-to-active-session behavior is implied but not explicitly stated in the description.

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