Delegate bounded coding tasks to configured OpenAI-compatible models with explicit working directory, read/write paths, diff validation, and optional verification commands, blocking sensitive changes.
Run a bounded coding task through the configured provider.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | Yes | ||
| task | Yes | ||
| model | No | ||
| forbidden | No | ||
| read_paths | Yes | ||
| validation | No | ||
| write_paths | Yes | ||
| timeout_seconds | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden and mostly fails. It says nothing about whether this is asynchronous (the existence of get_task_status and cancel_task strongly implies it), what write_paths actually modifies, sandboxing, cost, or what the timeout bounds mean. 'Bounded' gestures at a constraint without disclosing it.
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, so structurally it is efficient. But the brevity reflects under-specification rather than discipline; it omits information the agent needs.
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?
This is a high-complexity tool: 8 parameters (4 required), no annotations, no output schema, and an implied async/external-provider execution model. The one-sentence description covers none of the parameters, lifecycle, or side effects, leaving the definition far short of what an agent needs to invoke it correctly.
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% across 8 parameters, and the description adds no meaning for any of them. Critical fields like read_paths, write_paths, forbidden, validation, and timeout_seconds are completely unexplained in both the schema and the 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?
Names a specific verb and resource ('Run a bounded coding task') and hints at an execution model ('through the configured provider'). However, 'bounded' and 'configured provider' are undefined jargon, and the description does nothing to distinguish it from the sibling route_code_task, which by name alone seems closely related.
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 when-to-use guidance is given at all. The most pressing question an agent faces — delegate vs. route (route_code_task) — is left entirely unaddressed, and there is no mention of prerequisites or how this interacts with get_task_status/cancel_task.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.