Classify Python API calls for safety before running them, identifying safe, potentially modal, unsafe, or unknown actions without executing or altering the scene.
Classify visible calls as safe, potentially modal, unsafe or unknown without execution. Does not mutate the MD scene.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does well by disclosing that the tool does not execute and does not mutate the MD scene. It also communicates that it classifies into four named risk categories. It could still be more explicit about return format or failure behavior, but the key safety traits are covered.
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?
One sentence, clear, and front-loaded with the primary action and classification categories. Every word earns its place; the no-mutation guarantee is a useful addition without bloat.
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 a single-parameter classification tool, the description covers the core behavior and safety profile. However, it lacks explicit parameter semantics and does not describe the output shape, and there is no output schema to fill that gap. It is functional but not fully self-sufficient.
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 description never explains the 'code' parameter beyond what the schema shows, and schema coverage is 0%. It is likely Python source text, but an agent cannot tell whether to pass source code, a file path, or a module reference. With low schema coverage, the description needed to compensate but did not.
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 states a specific verb ('Classify') and resource ('visible calls') and names the classification categories. It distinguishes itself from execute_python by explicitly saying 'without execution', though the phrase 'visible calls' is somewhat jargon and could be clearer.
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 clear context that this is a non-executing analysis tool, but it does not explicitly state when to use it versus alternatives like execute_python. The 'preflight' name and 'without execution' imply the intended use before running code, but no direct when-to-use or when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.