Agent tools
Browser tools for pages that need more than a fetch.
Fetch JS-heavy pages and run browser-backed sessions.
What the agent can use
Browser use
Provide the target URL and the fields you need. State whether the task is read-only and identify any action that needs your approval.
Fetch JS-heavy page
Fetch a public URL with a browser-backed fallback.
Browser session
Run an explicit browser session for a public page.
Try a task
Make the result easy to verify.
Choose an agent and review its enabled tools. Capability calls can incur usage charges in addition to model and runtime costs; check the current catalog before running a batch.
Provide the input
Provide the target URL and the fields you need. State whether the task is read-only and identify any action that needs your approval.
Use this example request
Open this public page and extract the product names and visible availability. Include the URL and report any content you could not load.
Inspect the actual output
Compare the extracted fields with the rendered page. Check the actual resulting page or record for any authorized interaction.
Fit and limits
Check the tool against the task.
JavaScript rendering does not confer access to accounts, bypass site restrictions or guarantee that every interaction succeeds. Use authenticated connectors where application access is required.
Direct API integration
The API catalog lists the currently exposed direct endpoints, input fields, limits and pricing. The agent capability set and direct API catalog are different surfaces; not every capability has an equivalent direct endpoint. Provider documentation describes the provider API; it does not guarantee that every provider option is exposed through AgentSky.
A failed call is not a result
If the call fails, inspect the error and required input before retrying. Do not treat an agent's description of an output as evidence that the tool produced it.
Common questions
Browser use questions
Is this the same as a model?
No. A model reasons about the task; a tool performs a particular operation. The selected agent must have access to the needed capability.
Where do I find request fields and prices?
Use the live tool API catalog for current endpoints, schemas, limits and pricing. Agent execution can also incur model and runtime charges.
How do I know the result is usable?
Compare the extracted fields with the rendered page. Check the actual resulting page or record for any authorized interaction.