opencode_health

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 is a read-only reporting tool by nature (returns a report), which is implicitly safe. However, it doesn't detail whether the report reflects live state or cached data, whether the tool requires an active session, or what happens if session_id is invalid or stale. The field list is informative but behavioral specifics are thin.

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?

The description is a single well-structured sentence that front-loads the core purpose ('Returns a full health report for a session') followed by a comma-separated enumeration of the report's contents. It's efficient with no wasted words or redundancy, though the long field enumeration adds moderate length.

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?

The tool has 1 parameter, is fully schema-covered, and no output schema exists. Given its simplicity, the description reasonably captures the report's contents. However, without an output schema and with no annotations, the description must fully communicate what the report contains — and while it lists field names, it doesn't explain their meaning or format. For a reporting tool this is a mild completeness gap, but adequate for the tool's low complexity.

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%: the single parameter session_id is documented as 'Session ID (defaults to active session)'. The description's mention of 'for a session' aligns with this. Baseline 3 is appropriate since the schema already fully documents the parameter with its default behavior. The description adds no additional param detail beyond what the schema states.

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 tool returns a health report for a session, listing eight specific data points (status, uptime, last activity, output line count, recovery attempts, contract violations, file change count, operation log count). It uses a specific verb ('returns') and resource ('session health report'), and is distinguishable from siblings like opencode_status (session status) and opencode_server_health (server-level health). It doesn't explicitly name its sibling differentiation but the specificity of a 'full health report' with enumerated fields distinguishes it.

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 ('for a session') but provides no explicit when-to-use or when-not-to-use guidance. It doesn't mention when to prefer opencode_status over this tool or how it relates to opencode_server_health. The session scoping is clear, but no exclusions or alternatives are named.

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