OpenCode Session Depot

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description adds critical behavioral detail: 'Archive/unarchive/rename are reversible; delete is permanent (FK cascade).' It also explains the semantic differences between search, rag, and code, and the indexing prerequisites. This is substantial context that annotations alone do not provide.

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 dense but well-structured: a one-line action summary, focused bullet points on behavior, a clear return format block, and practical examples. Every line earns its place without redundancy or fluff.

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 the tool's complexity (14 actions, 12 parameters), the description covers all main usage modes, dependencies (e.g., `uv sync --extra rag`), side effects (permanent delete), and a return format. The output schema already exists, so detailed return fields are unnecessary in the description. This is complete for a tool of this scope.

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%, so the baseline is 3. The description adds value by showing concrete example parameter combinations (e.g., opencode_depot(action='code', query='extracted the auth module', path_filter='src')) and by explaining how parameters like `path_filter` and `query` are used differently in the code action. This goes beyond the schema descriptions.

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 opens with a clear enumeration of actions: 'list, inspect, archive/unarchive, rename, delete, search transcripts, semantic RAG search, code-recall search, or stats.' It also distinguishes the tool from siblings by stating 'Reads opencode's SQLite depot directly - works without `opencode serve`.' This makes the resource and scope unambiguous.

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 provides strong usage context: direct DB access without the server, and ample guidance on choosing between actions (search vs rag vs code). It also flags setup requirements: 'rag/code need `uv sync --extra rag` and an index pass.' However, it does not explicitly name alternative sibling tools or state when NOT to use this tool, so it stops short of a 5.

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