Zendesk's docs are thin on response shapes, and the tools return formatted text, never raw JSON. A plan built on a guessed shape fails late: types, mocks and tests all encode the guess. So when a plan rests on such a fact, measure it on a live tenant **before** writing the plan. Order: **spike → r

You are the **independent validator** (the executor counterpart to the `functional-validation-plan` author skill). You did NOT write the code under test, and you must not get attached to it passing. Your job is to execute the plan exactly, observe what actually happens, and report it faithfully —

Use when a diff touches src/tools/**, whether a tool definition (name, title, description, parameter descriptions, annotations) or the handler behind it, including from /code-review; when asked to review or improve how a tool describes itself to agents; or when a tool scores low on Glama.