> ## Documentation Index > Fetch the complete documentation index at: https://docs.thecontextcompany.com/llms.txt > Use this file to discover all available pages before exploring further. # Tools and models > Analyze which tools and models your agent uses, how often they fail, and how they contribute to cost, latency, and failures. Tools and models are first-class analytical dimensions. Every [tool call](/concepts#tool-calls) and every [model step](/concepts#steps) is captured with its arguments, results, latency, and cost, so you can rank, filter, and investigate at the tool or model level. ## Tools The Context Company records every tool invocation the agent makes: the tool name, the arguments passed, the result returned, whether it succeeded or errored, and its latency. ### What you can analyze * Which tools are called most frequently. * Which tools have the highest error rate. * Which recurring [failures](/analyze/failures) involve a particular tool. * Which arguments were passed to a specific tool over a time range. * What results the tool returned, including for failing runs. * Which tools contribute most to latency. * Which tool sequences commonly precede an error or negative feedback. ### API and MCP ```bash theme={null} GET /v1/tools?range=2w ``` Returns a breakdown of tool usage. See the [API reference](/access-data/api#tools). MCP calls like `get_agent_runs` accept `failureContains` and `onlyErrored`, so you can pull runs where a specific tool failed directly into your coding agent's context. ### Example questions > Which tool is responsible for the most failed runs in the last week? > Find runs where the `search` tool returned an empty result and the agent still produced a confident answer. > What arguments were passed to `issueRefund` in the runs that errored? ## Models Model steps record which model was used, the input and output tokens, the resulting cost, latency, and any error at the step level. ### What you can analyze * Models used, aggregated by run count, tokens, and cost. * Cost and token usage per model over time. * Latency per model. * Error rate per model where measurable. * Comparisons between models on the same task. * Filter any other analysis to a specific model. ### API ```bash theme={null} GET /v1/models?range=2w ``` Returns a breakdown of model usage. See the [API reference](/access-data/api#models). ### Example questions > How have my costs shifted between models this month? > Which models are slowest on multi-turn conversations over 5 messages? > Did failure rate increase after we switched to `gpt-4o-mini` on the `summarize` step? ## Tools and models in Insight Search Because tool and model dimensions are indexed as native columns, Insight Search can join them freely with any other dimension: > Find runs where the `search` tool was called after the `summarize` tool, on `gpt-4o`, for organizations on the enterprise plan, where the final response didn't answer the user's question. ## Limitations * Arguments and results are captured as recorded by the instrumentation. If your framework does not expose a tool's arguments (rare), that field will be empty for those calls. * Model-level cost depends on the framework surfacing token counts. All supported frameworks do; custom instrumentation is responsible for reporting tokens. ## Related See tool and model behavior inside a single run. Runtime errors grouped, including tool-call errors. Ask cross-dimensional questions about tools and models. The exact fields recorded per tool call and model step.