Summarize an OpenCode session with a specified provider and model, condensing long conversations into a concise overview.
Summarize a session using a model. Long-running (30-60s+).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| modelID | Yes | ||
| variant | No | ||
| directory | No | Project directory to target. Optional; defaults to the server default project. | |
| providerID | Yes |
Changes observed during successful MCP inspections.
v3.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full disclosure burden. It does add a genuinely useful operational trait — 'Long-running (30-60s+)' — which warns the agent about latency. However, it omits permissions required, whether the operation persists or mutates session state, and what the summary contains.
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 compact sentences with zero filler, and the primary purpose is front-loaded ahead of the latency caveat. Every word 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?
No output schema and no annotations, over a 5-parameter tool with only 20% schema coverage. The description should compensate for the missing parameter docs and lack of behavioral detail but does not, leaving the agent under-informed about invocation specifics.
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 only 20% (just 'directory'), yet the description explains none of the five parameters. The roles of id, providerID, modelID, and variant — and why provider/model are required to summarize — are undocumented in both schema and description.
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 (summarize) applied to a specific resource (a session), with the added qualifier 'using a model'. This is clearly distinguishable from siblings like session_diff, session_list, or session_get, which perform different operations on the same resource.
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?
No guidance on when to use this versus alternatives, no prerequisites, and no exclusions. The agent is left to infer when summarizing is appropriate versus, say, session_diff or session_get.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.