Classify coding tasks by risk and automatically delegate safe, bounded local work to a discounted model tier while blocking sensitive changes such as auth, payments, or production.
Classify a coding task by risk and automatically delegate safe work to the discounted model tier.
| 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?
With no annotations, the description carries the full behavioral burden and falls short. It implies file reads and writes (mirrored by read_paths/write_paths) and mentions a 'discounted model tier' cost angle, but discloses nothing about permissions required, what happens to rejected/unsafe tasks, whether file changes are reversible, or any timeout/rate behavior.
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 padding, which is structurally clean. It is arguably too terse for an 8-parameter tool, but that shortfall is better attributed to completeness than to verbosity.
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 complex tool with 8 parameters (4 required), 0% schema coverage, no annotations, and no output schema, and the description supplies almost none of the missing context. An agent cannot determine how the risk classifier behaves, what the safety boundary is, or what any parameter should contain.
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, so the description must compensate and largely does not. Only the 'discounted model tier' phrasing loosely gestures at the model parameter, while cwd, read_paths, write_paths, forbidden, validation, and timeout_seconds receive no explanation, and it is unclear whether the model enum is auto-selected or must be supplied.
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 phrase ('classify a coding task by risk') and a concrete outcome ('automatically delegate safe work to the discounted model tier'), so the agent understands this is an auto-routing wrapper. It does not, however, explicitly contrast itself with the sibling delegate_code_task, leaving the manual-vs-automatic distinction to inference.
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 or when-not-to-use guidance is given, and the nearest alternative (delegate_code_task) is never named. The description implies this tool handles routing decisions automatically, but the agent is not told what qualifies as 'safe' or what it should do when the risk classification rejects the task.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.