Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- read_pipeline_coverage — Report what a sales pipeline actually holds — per stage, under YOUR stage names, with each stage's share and a coverage ratio when you name a quota. Weighted ONLY by win rates you supply, each shown with the number of closed deals it was measured over. No forecast of a future period, and no confidence interval: the agent this replaces applied a fixed 15 percent band its own comment records as a ticket's accuracy target.
- project_from_history — Apply the conversion YOUR pipeline has actually achieved to the pipeline you hold now. The method is one division per period: what share of the pipeline open at its start closed. The answer is the RANGE your history contains, with the mean beside it and never instead of it. No smoothing constant, no confidence level, and no single headline number — the agents this replaces smoothed with a fixed alpha and wrapped the result in a band their own comment records as a ticket's accuracy target.
- run_full — Run every capability you supplied the input for, in registry order, and return one report. Capabilities whose input is missing are listed as skipped with the fields they need — never run against a fixture and never reported as zero.
- list_capabilities — List what this agent can do: every tool it advertises, what each one is for, and the arguments each one reads. Useful for discovery before the first call.
- plan_inputs — Plan the inputs for a tool: returns the questions to ask, the JSON schema of the arguments, and a ready-to-edit example. Every argument it names is an argument the tool actually reads.
- discover_intent — Understand your goal and co-design the exact input through clarifying questions before anything runs.
- open_form — Use this the moment the user wants to run this agent on their own input. It opens an interactive form that collects the run arguments. Do NOT check credentials, do NOT ask clarifying questions in chat, and do NOT run any analysis before calling this — the form is the entry point for running the agent.
- run_form — Internal: invoked by the open_form form when the user submits. Reads exactly the same arguments as run_full and forwards all of them. Not for direct use.
