Create a native provider session for supported coding agents, specifying provider and optional working directory or title to enable coordinated message passing across isolated environments.
Create a native provider session when supported.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | ||
| title | No | ||
| provider | Yes |
Changes observed during successful MCP inspections.
v0.2.18Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already communicate that this operation is not read-only and not destructive, so the description does not need to restate that. The phrase 'when supported' adds a useful behavioral caveat that some providers may not allow native session creation. However, the description does not disclose failure behavior, side effects, or whether an existing session may be replaced.
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, front-loaded sentence with no filler words. It is appropriately brief for the core action, though it sacrifices beneficial detail for brevity. It earns its place but does not go beyond the minimum.
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?
With three parameters, no output schema, and no parameter descriptions, the tool needs more context to be safely invoked. The description does not explain what a 'native provider session' is, how unsupported providers are handled, or how cwd and title influence the session. The annotations provide only basic mutation hints, leaving the agent under-informed.
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?
The schema has 0% description coverage, so the description carries the full burden of explaining parameters, but it mentions none of provider, cwd, or title. The enum in the schema lists provider values, yet the description does not clarify how provider affects support or what cwd and title mean. This is a significant gap for an agent trying to construct a correct invocation.
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 identifies the action (create) and the resource (native provider session), which is sufficiently specific to distinguish it from session_resume and session_set_model among siblings. The qualifier 'when supported' adds a condition but does not undercut the core purpose. It is not a tautology and conveys the basic operation clearly.
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 no guidance on when to use session_create versus session_resume, session_set_model, or other session-related tools. It does not state prerequisites, typical invocation context, or when the 'supported' condition is likely to be true. Usage context is only weakly implied by the verb 'create'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.