terse-sharplisted

# TerseSharp TerseSharp answers C# and XAML questions **semantically**, from a Roslyn workspace that is already loaded. Reading a `.cs` file whole, or grepping for a type name, costs 10-30x more tokens and returns matches that are not references. ## Route every question by its target **Every C#/.NET question has a tool, and the table below names it.** Read the left column, take the tool on the right, call it — that is the whole working rule, and it is the one thing to remember from this document. It holds for `.cs`, `.razor`, `.cshtml`, `.csproj`, `.props`, `.targets`, `.sln`/`.slnx`/`.slnf`, `.xaml`, `.axaml`, `.paml`, `.resx` and `.resw`, and for every question about C# symbols, references, diagnostics, builds, tests or the working tree. The rules that keep it that way — what the guard denies, what to do when a tool errors, and the tripwires — are the hard gate directly **below** the table. ## The whole surface — one row per job Read the **Job** column for what you want, the **Instead of** column for the built-in it retires, and call what is in **Use**. Every tool the server advertises is in this table exactly once. | Job | Instead of | Use | Why | |---|---|---|---| | **Workspace** | — | `workspace_status` | solution, worktree, branch, project and document counts, plus `advertised=<n> tools <t> tokens` for what this session's `tools/list` really costs - `verbose=true` splits that total into `toolDescriptions`, `parameterDescriptions`, `schemaFrame` and `names`; its l