Rank optimal multi-tool execution routes for any task. Use LLM scoring to select the best path based on speed, simplicity, or reliability preferences.
Use LLM intelligence to score and rank optimal multi-tool execution routes. [Legacy compat API — prefer agent_run when MITOSIS_AGENT_ENABLED=true.]
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | Task description | |
| criteria | No |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears the full burden of behavioral disclosure. It mentions that the tool uses LLM intelligence and is a legacy API, but it does not disclose side effects, output format, latency/cost implications, or failure modes. Score and rank implies non-mutating behavior, but that is implicit.
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 that states purpose and legacy status without wasted words. The legacy note is packed into a compact bracketed clause that adds actionable routing information.
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 tool has a nested criteria object, no output schema, and no annotations, yet the description does not explain what the output looks like or how criteria affect behavior. The legacy note helps routing, but an agent would still be under-informed about expected results and success conditions.
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 50% and the description adds no parameter-level guidance. The task field is only described as 'Task description' in the schema, and the criteria object's boolean options are names alone with no explanation of how they influence scoring or ranking.
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 uses a specific verb and resource: 'score and rank optimal multi-tool execution routes.' It also differentiates itself from agent_run by labeling this a legacy compatibility API, so an agent can tell what it does and how it relates to a sibling.
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 an explicit conditional alternative: prefer agent_run when MITOSIS_AGENT_ENABLED=true. This tells an agent when not to use this tool, though it does not spell out other comparison tools like generate_route_suggestions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.