A live demo with sample data: look around, nothing can be changed. Start a free trial or self-host it.

get_flight_price

Last 7 days

Calls

0

Nothing yet in this window

Error rate

0%

0 failed calls

Response time

-

median

Called from

-

Calls over time

CallsErrors
Show the numbers
Calls and errors per bucket
TimeCallsErrors
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00
00

Response times

Calls by how long they took

No calls in this window.

Repeated calls

Same arguments as the call before, in the same session

1 of 13 calls (8%)

An agent sending the same call again usually did not get what it needed from the answer: an error it could not act on, or a result it did not recognise as complete. Sessions show where it happened.

Right before it went wrong

Before 13 repeated or failed calls, in their sessions

What the agent called just before get_flight_price repeated itself or failed. One call standing out usually did not do what the agent expected: a click that did not land, a search that came back empty.

Called beforeClientRepeatedFailed
Prompt plan_tripCursor03
get_flight_statusCursor02
Prompt plan_tripChatGPT02
Prompt plan_tripClaude Code02
get_flight_priceClaude Code11
get_flight_statusClaude01
get_flight_statusMCP Inspector01
search_flightsClaude Code01

How it fails

Nothing failed in this window.

Called from

Not called in this window.

Parameters agents send

Names and types only

Not called in this window.