docs: revise docs to align with updated semantics

Author: tradeqvest

docs/agents.md

@@ -618,7 +618,7 @@ except UsageLimitExceeded as e:
 
 ##### Capping tool calls
 
-If you need a precise guardrail on the number of tool invocations within a single run (including retries that actually re-execute the tool), use `tool_calls_limit`:
+If you need a limit on the number of successful tool invocations within a single run, use `tool_calls_limit`:
 
 ```py
 from pydantic_ai import Agent
@@ -640,7 +640,7 @@ except UsageLimitExceeded as e:
 ```
 
 !!! note
-    - Usage limits are especially relevant if you've registered many tools. Use `request_limit` to bound the number of model turns, and `tool_calls_limit` to cap the exact number of successful tool executions within a run.
+    - Usage limits are especially relevant if you've registered many tools. Use `request_limit` to bound the number of model turns, and `tool_calls_limit` to cap the number of successful tool executions within a run.
     - These limits are enforced at the final stage before the LLM is called. If your limits are stricter than your retry settings, the usage limit will be reached before all retries are attempted.
 
 #### Model (Run) Settings

docs/tools.md

@@ -1036,8 +1036,8 @@ When a model returns multiple tool calls in one response, Pydantic AI schedules
 
 Async functions are run on the event loop, while sync functions are offloaded to threads. To get the best performance, _always_ use an async function _unless_ you're doing blocking I/O (and there's no way to use a non-blocking library instead) or CPU-bound work (like `numpy` or `scikit-learn` operations), so that simple functions are not offloaded to threads unnecessarily.
 
-!!! note "Limiting exact tool executions"
-    You can cap the exact number of tool executions within a run using `UsageLimits(tool_calls_limit=...)`. The counter increments after each successful tool invocation. Note that output tools (used for structured output) are not counted in the `tool_calls` metric.
+!!! note "Limiting tool executions"
+    You can cap tool executions within a run using `UsageLimits(tool_calls_limit=...)`. The counter increments only after a successful tool invocation. Output tools (used for structured output) are not counted in the `tool_calls` metric.
 
 ## Third-Party Tools