Begin a new task episode and receive the episode ID, instructions, and tool budget needed to work through professional decision cases.
Start a new task episode. Returns the episode id, the instructions and the tool budget.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | No | Optional specific task id | |
| taskset | No | Optional task set: patents-first-action (default), patents-response or patents-appeal |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses the return payload (episode id, instructions, tool budget), which matters since there is no output schema, but it says nothing about state effects, whether a prior episode is replaced, or any auth/permission requirements.
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 short, front-loaded sentences with zero filler: what it does, then what it returns. Nothing is wasted.
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 an episode-initialization tool the essentials are present (action, returns, both params documented in schema), but the lack of any pruning on prerequisites, call ordering, or interaction with submit_answer leaves the agent to infer the workflow.
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 100% and both parameters are documented there, including the enum-like taskset values and the default. The description adds no parameter-level detail, so the baseline of 3 applies.
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+resource ('Start a new task episode') that is clearly distinct from the read/search siblings. It does not explicitly name any sibling, but no other tool in the list initiates an episode, so disambiguation is implicit.
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?
There is no guidance on when to call this versus the alternatives, nor any mention of prerequisites or ordering relative to submit_answer, which is presumably the counterpart that ends an episode. Usage is only inferable from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.