Plan a starter project run from selected papers and workspace paths without writing files, so you can preview artifacts, queues, and sessions before execution.
Plan a Workspace Starter run without writing files.
| Name | Required | Description | Default |
|---|---|---|---|
| focus | No | ||
| papers | Yes | ||
| artifact_dir | Yes | ||
| create_queue | No | ||
| project_title | No | ||
| create_session | No | ||
| max_candidates | No | ||
| workspace_path | Yes | ||
| target_result_id | No |
Changes observed during successful MCP inspections.
v1.2.2Input schema / properties / max_candidates / maximumAdded value: +20Input schema / properties / max_candidates / minimumAdded value: +1v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It usefully discloses the key trait that no files are written (safe/dry-run), which is genuinely valuable. But it says nothing about what the plan output contains, what the create_queue/create_session flags imply for a supposedly non-writing tool, or any preconditions or auth needs.
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?
A single front-loaded sentence with no filler, which is efficient. For a 9-parameter tool it is arguably under-specified rather than concise, but there is no padding or redundancy.
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 9-param tool with no annotations, no output schema, and 0% schema coverage, the description is far too thin. The dry-run trait is the only substantive information; nothing about required inputs, what the plan returns, or how the boolean flags interact is covered.
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 0% with 9 parameters, including non-obvious ones like create_queue, create_session, target_result_id, max_candidates, and artifact_dir. The description adds zero parameter meaning, leaving an agent to guess the semantics of every argument.
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 the verb 'Plan' and a resource ('Workspace Starter run'), and adds the distinguishing trait 'without writing files'. However, 'Workspace Starter run' is internal jargon not defined anywhere, and it does not name or contrast with any sibling such as workspace_bootstrap_reading_project or the other workspace_plan_* tools, so an agent cannot confidently tell what a 'Starter run' actually plans.
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 phrase 'without writing files' hints at a preview/dry-run use case, but there is no explicit when-to-use, when-not-to-use, or alternative named. With siblings like workspace_plan_external_imports_for_result and workspace_bootstrap_reading_project, guidance on which planning entry point to pick is needed and absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.