Skip to main content

Class: SelfEvaluateTool

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:160

ITool implementation enabling agents to evaluate their own responses, adjust runtime parameters, and generate performance reports.

Example​

const tool = new SelfEvaluateTool({
  config: {
    autoAdjust: false,
    adjustableParams: ['temperature', 'verbosity'],
    maxEvaluationsPerSession: 20,
  },
});

const result = await tool.execute({
  action: 'evaluate',
  response: 'The capital of France is Paris.',
  query: 'What is the capital of France?',
}, context);

Implements​

  • ITool<SelfEvaluateInput>

Constructors​

Constructor​

new SelfEvaluateTool(deps): SelfEvaluateTool

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:235

Create a new SelfEvaluateTool.

Parameters​

deps​

SelfEvaluateDeps

Injected dependencies including config, optional adaptPersonality tool, and optional memory store callback.

Returns​

SelfEvaluateTool

Properties​

category​

readonly category: "emergent" = 'emergent'

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:177

Optional

Optional. A category or group to which this tool belongs (e.g., "data_analysis", "communication", "file_system", "image_generation"). This is useful for organizing tools, for filtering in UIs or registries, and potentially for aiding an LLM in selecting from a large set of tools.

Implementation of​

ITool.category

description​

readonly description: string

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:171

A detailed, natural language description of what the tool does, its primary purpose, typical use cases, and any important considerations or limitations for its use. This description is critical for an LLM to understand the tool's capabilities and make informed decisions about when and how to invoke it. It should be comprehensive enough for the LLM to grasp the tool's semantics.

Implementation of​

ITool.description

displayName​

readonly displayName: "Self Evaluate" = 'Self Evaluate'

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:168

A concise, human-readable title or display name for the tool. Used in user interfaces, logs, or when presenting tool options to developers or users.

Example​

"Web Search Engine", "Advanced Python Code Interpreter"

Implementation of​

ITool.displayName

hasSideEffects​

readonly hasSideEffects: false = false

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:180

Optional

Optional. Indicates if the tool might have side effects on external systems (e.g., writing to a database, sending an email, making a purchase, modifying a file). Defaults to false if not specified. LLMs or orchestrators might handle tools with side effects with greater caution, potentially requiring explicit user confirmation.

Implementation of​

ITool.hasSideEffects

id​

readonly id: "com.framers.emergent.self-evaluate" = 'com.framers.emergent.self-evaluate'

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:162

A globally unique identifier for this specific tool (e.g., "web-search-engine-v1.2", "stock-price-fetcher"). This ID is used for internal registration, management, and precise identification. It's recommended to use a namespaced, versioned format (e.g., vendor-toolname-version).

Implementation of​

ITool.id

inputSchema​

readonly inputSchema: JSONSchemaObject

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:183

The JSON schema defining the structure, types, and constraints of the input arguments object that this tool expects. This schema is used by:

  1. LLMs: To construct valid argument objects when requesting a tool call.
  2. ToolExecutor: For validating the arguments before invoking the tool's execute method. It should follow the JSON Schema specification.

See​

https://json-schema.org/

Implementation of​

ITool.inputSchema

name​

readonly name: "self_evaluate" = 'self_evaluate'

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:165

The functional name of the tool, as it should be presented to and used by an LLM in a tool call request (e.g., "searchWeb", "executePythonCode", "getWeatherForecast"). This name must be unique among the set of tools made available to a given GMI/LLM at any time. It should be concise, descriptive, and typically in camelCase or snake_case.

Implementation of​

ITool.name

Methods​

execute()​

execute(args, context): Promise<ToolExecutionResult<any>>

Defined in: packages/agentos/src/emergent/SelfEvaluateTool.ts:250

Execute the requested self-evaluation action.

Parameters​

args​

SelfEvaluateInput

Action type and associated parameters.

context​

ToolExecutionContext

Tool execution context.

Returns​

Promise<ToolExecutionResult<any>>

A ToolExecutionResult wrapping the action outcome.

Implementation of​

ITool.execute