Agent tools
Research search results with a defined location and language.
Fetch SEO/SERP data.
What the agent can use
Search SERP
Provide the queries, target market and language. Start with a small batch and check the available endpoint fields and price.
Search SERP
Fetch SEO/SERP data.
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 queries, target market and language. Start with a small batch and check the available endpoint fields and price.
Use this example request
Inspect search results for these queries in the specified location and language. Return the observed URLs and separate observations from recommendations.
Inspect the actual output
Check that the returned search context matches the requested location and language. Keep the collection time with the observations; rankings can change.
Fit and limits
Check the tool against the task.
A search result sample is not search volume, an attribution report or proof that an AI answer will cite your page. Review current capability settings before running paid batches.
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
Search SERP 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?
Check that the returned search context matches the requested location and language. Keep the collection time with the observations; rankings can change.