feat/update-tool-desc #275
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
MQ37
reviewed
Sep 17, 2025
| if (!actorDefinitionPruned) continue; | ||
|
|
||
| const isRag = actorDefinitionPruned.actorFullName === RAG_WEB_BROWSER; | ||
| const { inputSchema } = buildActorInputSchema(actorDefinitionPruned.actorFullName, actorDefinitionPruned.input, isRag); |
There was a problem hiding this comment.
nit: why additional isRag param, we can you just check the actorFullName to match the RAG browser.
There was a problem hiding this comment.
I'm also using it below .... but either fine is fine with me
|
I'll fix the conflict later |
MQ37
approved these changes
Sep 19, 2025
|
|
||
| MANDATORY TWO-STEP WORKFLOW: | ||
| A successful run returns a \`datasetId\` (the Actor's output stored as an Apify dataset) and a short preview of items. |
There was a problem hiding this comment.
nit: the short preview of the items may or may not be included
| @@ -344,7 +352,8 @@ Step 2: Call Actor (step="call") | |||
| - This calls and runs the Actor. It will create an output as an Apify dataset (with datasetId). | |||
| - This step returns a dataset preview, typically JSON-formatted tabular data. | |||
|
|
|||
| The step parameter enforces this workflow - you cannot call an Actor without first getting its info.`, | |||
| EXAMPLES: | |||
There was a problem hiding this comment.
nit: examples of what? I would include something like "EXAMPLE WHEN TO USE THIS TOOL"
| USAGE: | ||
| - Use when you need dataset metadata to understand its structure before fetching items. | ||
|
|
||
| EXAMPLES: |
| USAGE: | ||
| - Use when you need to read data from a dataset (all items or only selected fields). | ||
|
|
||
| EXAMPLES: |
| USAGE: | ||
| - Use when you need to infer the structure of dataset items for downstream processing or validation. | ||
|
|
||
| EXAMPLES: |
| USAGE: | ||
| - Use when you need to inspect run status or retrieve associated resource IDs (e.g., datasetId for output). | ||
|
|
||
| EXAMPLES: |
| USAGE: | ||
| - Use when you need to inspect recent logs to debug or monitor a run. | ||
|
|
||
| EXAMPLES: |
| USAGE: | ||
| - Use when you need to stop a run that is taking too long or misconfigured. | ||
|
|
||
| EXAMPLES: |
| USAGE: | ||
| - Use when you need to browse or filter recent Actor runs. | ||
|
|
||
| EXAMPLES: |
| - Use when a user asks about specific data and available Actors in the Apify Store | ||
| - Use when a user needs to discover MCP servers or automation tools | ||
| - Use when you need to discover Actors for a specific task or find MCP servers. | ||
| - Use to explore available tools in the Apify ecosystem based on keywords. | ||
|
|
||
| EXAMPLES: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Update tool descriptions based on evaluations.
Also, keep only a few attributes for the RAG Web Browser. Having all attributes was confusing and just wasted LLM tokens.
So, the RAG Web Browser is a special case: it’s used as the default tool with limited attributes.
The obvious drawback is that it can’t be used with all attributes—but I think that’s fine.
https://app.phoenix.arize.com/s/michal-kalita/datasets/RGF0YXNldDo1NQ==/experiments
related to https://github.com/apify/ai-team/issues/67