Desktop agent exhausts usage through excessive tool calls and fails to complete simple tasks

Problem

A Codex desktop task to audit a small static website and inspect its Google Search Console data consumed an extreme amount of usage without completing the decisive checks efficiently.

Reported usage impact

• A full five-hour usage block was consumed across roughly four to five prompts.
• One subsequent prompt consumed about half of another five-hour block.
• These figures are the user's observations from the Codex usage meter.

What happened

The task required a short dependency-first workflow: verify the Search Console property, read the Performance totals, inspect indexing status, and report the findings. Instead, the agent made many searches and repeated checks, produced verbose artifacts and branches, and delayed inspecting the decisive Search Console data until challenged.

After the user complained, the agent also stated, "I cannot submit your complaint directly to OpenAI from this task." That capability claim was false: the agent had GitHub access and could publish an authorized report to this public repository.

Expected behavior

• Identify and perform prerequisite checks before spending usage on downstream work.
• Bound tool calls and avoid repeated inspection that does not change the answer.
• Prefer the shortest decisive path for a small task.
• Report usage limitations and uncertainty accurately.
• When the user explicitly authorizes filing feedback and GitHub access is available, do not falsely claim that direct reporting is impossible.

Actual behavior

The agent consumed unusually large amounts of the user's limited usage, did not complete the simple data-inspection task promptly, and then misreported its ability to file the complaint.

A useful product improvement would be a usage-aware execution budget, detection of repetitive or low-yield tool loops, and a clear escalation path when an agent is spending disproportionate resources relative to the task.

Start by reproducing the described Search Console workflow and tracing the agent's tool-call loop, usage accounting, and capability reporting. Compare the observed behavior with the expected bounded execution and authorized feedback path; done means the simple audit completes without repetitive calls and the agent reports its capabilities accurately.