Tool result bloat

A tool result is paid for more than once: it enters the context on the turn it arrives and is re-transmitted with every turn after that, multiplying its size by the remaining conversation length. A 20KB JSON response early in a long session costs far more than the same response near the end — position compounds size.

An agent calls a search tool that returns a full response object — headers, metadata, twenty results — when the task needs three titles. Every subsequent reasoning step re-sends the whole object. Truncating or summarising at the tool boundary shrinks every following call.

By tool-result token counts per call, which Capsera extracts as structural metadata. A high ratio of tool-result tokens to completion tokens marks the agents worth fixing first.

What is tool result bloat?

Tool result bloat is the cost incurred when large tool outputs — full API payloads, whole files, verbose logs — are inserted into an agent's context and then re-sent on every subsequent turn. The result is paid for once when it arrives and again on every turn after it. Its true cost is therefore its size multiplied by the remaining length of the session.

• Context regrowth — Context regrowth is the compounding cost of re-sending an entire conversation history with every turn, so total input tokens grow roughly with the square of the conversation length.
• Cost defect — A cost defect is a pattern in code that makes an LLM workload cost more than the same behaviour would cost if written differently.
• Cost per run — Cost per run is the total LLM spend attributed to one execution of an agent task, summed across every call, model, and agent that execution triggered.