docs: reframe deep_search guidance around research depth

The instructions and docs led with the costs of Exa's premium mode
(slower, pricier). Same steering -- the model still reserves deep_search
for questions that need it -- now framed by what a call invests (a full
research pass, Exa's research-grade mode) rather than what it costs.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docs/exa-search.md

@@ -72,9 +72,9 @@ hard error: the run continues and the model can correct the URL or rephrase.
 `deep_search` calls Exa search with `type='deep'` and a plain-text output
 schema: Exa expands the question into multiple queries, searches, and returns
 an answer grounded in citations -- all in **one tool call**, with the cited
-sources listed under the answer. It is markedly slower and more expensive per
-call than `web_search`, and the model decides when to invoke tools, so the
-tool is off by default -- enable it explicitly:
+sources listed under the answer. Each call invests more time and search depth
+than `web_search` (Exa's research-grade mode), and the model decides when to
+invoke tools, so the tool is off by default -- enable it explicitly:
 
 ```python
 from pydantic_ai_harness.exa import ExaSearch

pydantic_ai_harness/exa/README.md

@@ -64,9 +64,9 @@ the run.
 `deep_search` calls Exa search with `type='deep'` and a plain-text output
 schema: Exa expands the question into multiple queries, searches, and returns
 an answer grounded in citations -- all in **one tool call**, with the cited
-sources listed under the answer. It is markedly slower and more expensive per
-call than `web_search`, and the model decides when to invoke tools, so the
-tool is off by default -- enable it explicitly:
+sources listed under the answer. Each call invests more time and search depth
+than `web_search` (Exa's research-grade mode), and the model decides when to
+invoke tools, so the tool is off by default -- enable it explicitly:
 
 ```python
 from pydantic_ai_harness.exa import ExaSearch

pydantic_ai_harness/exa/_capability.py

@@ -17,8 +17,8 @@ _INSTRUCTIONS = (
 )
 
 _DEEP_INSTRUCTIONS = _INSTRUCTIONS + (
-    ' For questions that need synthesis across many sources, escalate to `deep_search`: it is '
-    'slower and costs more per call, but returns a cited answer in one step.'
+    ' For questions that need synthesis across many sources, escalate to `deep_search`: it runs '
+    'a full research pass in a single call, so save it for the questions that deserve that depth.'
 )
 
 
@@ -57,9 +57,10 @@ class ExaSearch(AbstractCapability[AgentDepsT]):
     """Also expose the `deep_search` tool. Off by default.
 
     Deep search (Exa search `type='deep'`) runs a multi-step agentic search
-    and synthesizes a cited answer in one call. It is markedly slower and more
-    expensive per call than `web_search`, and the model decides when to invoke
-    tools, so the extra spend is opt-in rather than the default.
+    and synthesizes a cited answer in one call. Each call invests more time
+    and search depth than `web_search` (Exa's research-grade mode), and the
+    model decides when to invoke tools, so that investment is opt-in rather
+    than the default.
     """
 
     client: ExaClient | None = None

pydantic_ai_harness/exa/_toolset.py

@@ -136,9 +136,8 @@ class ExaSearchToolset(FunctionToolset[AgentDepsT]):
     async def deep_search(self, question: str) -> str:
         """Run Exa's multi-step deep search and return a synthesized answer with its sources.
 
-        Slower and more expensive per call than `web_search`; suited to
-        questions that need synthesis across many sources rather than a quick
-        survey.
+        A full research pass in a single call; suited to questions that need
+        synthesis across many sources rather than a quick survey.
 
         Args:
             question: The research question to answer.