# get_inference_tool

Get a Layer tool's fields on one of its base models, to fill in \`input\` for \`run\_inference\_tool\`.

Returns the tool's summary, the base model the fields are for and the JSON Schema of \`input\`.  
The schema says whether the tool works on a source file and whether the model takes a mask.

IMPORTANT: Call tool \`get\_instructions\` first for general platform guidance.

## Parameters

| Parameter                    | Type          | Default | Description                                                                                                                                                                                                           |
| ---------------------------- | ------------- | ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| project\_id                  | string (uuid) | —       | Optional project the work would be filed in: the models and defaults answered are those a run in it gets. Use \`list\_projects\` to find project ids. Without it or \`session\_id\`, the answer is for the workspace. |
| session\_id                  | string (uuid) | —       | Optional session the work would land in: the answer is for its project. With \`project\_id\`, the session must be in that project.                                                                                    |
| workspace\_idrequired        | string (uuid) | —       | The user's workspace id.                                                                                                                                                                                              |
| inference\_tool\_keyrequired | string        | —       | The tool's key, such as \`image.upscale\`, from \`list\_inference\_tools\`.                                                                                                                                           |
| base\_model\_id              | string        | —       | The base model whose fields to return, by ID, slug, name or alias: one of the tool's \`base\_model\_ids\`. Without it, the fields are for the model a run takes when it names none.                                   |