Creates a Web-visible DeepSeek Harness coding session in an existing workspace and returns a reusable session ID for delegating coding tasks without starting a model turn.
Create a Web-visible DSH coding-agent session in an existing absolute workspace. For code changes use an isolated worktree prepared by Codex. Returns reusable session_id. Does not start a model turn.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | Yes | ||
| title | Yes | Codex 委派任务 |
Changes observed during successful MCP inspections.
v0.3.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so well by disclosing key behaviors: the session is Web-visible, lives in an existing absolute workspace, returns a reusable session_id, and does not start a model turn. It could add authentication prerequisites or side-effect details, but the most important behavioral traits are present.
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?
Three sentences with no filler: the purpose is front-loaded, the alternative for code changes follows, and the return value plus turn behavior are stated compactly. Every sentence 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?
The description is adequate for a low-complexity 2-parameter tool and covers the core purpose, return value, and non-turn behavior, but it omits the meaning of title and any prerequisites such as authentication or connecting first. Given the sibling context includes dsh_authenticate and dsh_connect, that missing guidance leaves the definition slightly incomplete.
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%, so the description must explain the parameters, but it only indirectly implies cwd via 'existing absolute workspace' and never explains title at all. The default title is also left unexplained, leaving an agent without enough meaning to choose a good value confidently.
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 names a specific verb and resource: 'Create a Web-visible DSH coding-agent session' and constrains it to an 'existing absolute workspace.' The clause 'Does not start a model turn' distinguishes it from turn-driving siblings like dsh_send_message, so an agent can tell it apart from sibling tools without opening schemas.
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 gives practical guidance: 'For code changes use an isolated worktree prepared by Codex' states a clear when-not-to-use condition, and 'Does not start a model turn' clarifies its scope. It does not name a sibling alternative explicitly, but the context and exclusions are clear enough for choosing this tool over send_message or wait.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.