Skip to content

fix: improve Apify tools docstrings with Apify context#4

Open
jirispilka wants to merge 3 commits intoapify:feat/strands-core-apify-toolsfrom
jirispilka:feat/strands-core-apify-tools
Open

fix: improve Apify tools docstrings with Apify context#4
jirispilka wants to merge 3 commits intoapify:feat/strands-core-apify-toolsfrom
jirispilka:feat/strands-core-apify-tools

Conversation

@jirispilka
Copy link
Copy Markdown

Summary

  • Inject Apify platform context into module and tool docstrings (what an Actor is, what a dataset is, storage types)
  • Improve actor_id and run_input parameter descriptions to mention Apify Store
  • Expand crawler_type from a one-liner into three bullet points so the LLM can pick the right engine
  • Add cross-tool pointers (e.g. when to prefer apify_run_actor_and_get_dataset vs apify_run_actor)

🤖 Generated with Claude Code

@jirispilka jirispilka force-pushed the feat/strands-core-apify-tools branch from 365fb16 to 1b9675f Compare April 2, 2026 09:56
@jirispilka jirispilka mentioned this pull request Apr 2, 2026
7 tasks
Copy link
Copy Markdown
Collaborator

@daveomri daveomri left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks much better now, just a few notes.

@jirispilka jirispilka requested a review from daveomri April 8, 2026 07:05
Copy link
Copy Markdown
Collaborator

@daveomri daveomri left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks much better, pre-approving, but just a few notes:

- 📁 **File Operations** - Read, write, and edit files with syntax highlighting and intelligent modifications
- 🖥️ **Shell Integration** - Execute and interact with shell commands securely
- 🧠 **Memory** - Store user and agent memories across agent runs to provide personalized experiences with both Mem0, Amazon Bedrock Knowledge Bases, Elasticsearch, and MongoDB Atlas
- 🧠 **Memory** - Store user and agent memories across agent runs to provide personalized experiences with Mem0, Amazon Bedrock Knowledge Bases, Elasticsearch, and MongoDB Atlas
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not sure if we should change other parts of the README that don't involve the Apify tools, so we don't run into issues with the Strands review process.

)

# Connect to a SSE-based server
# Connect to an SSE-based server
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, I wouldn't change anything that's not necessary for the Apify tools.

)

# Convert HTML webpages to markdown for better readability
# Convert HTML webpages to Markdown for better readability
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, I wouldn't change anything that's not necessary for the Apify tool.

input schema - check the Actor README on Apify Store for required fields.
timeout_secs: Maximum time in seconds to wait for the Actor run to finish. Defaults to 300.
memory_mbytes: Memory allocation in MB for the Actor run.
memory_mbytes: Memory allocation in MB for the Actor run. Uses Actor default if not set.
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

just a nit: maybe adding "uses actor default memory if not set"

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe default value.. not sure what sounds better here

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants