Sapper Sweep

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full burden, and it does disclose the core loop semantics: all graphs are visited round-robin, each gets a per-round time budget, and the process terminates at a deadline. It does not disclose that this is a long-running blocking operation by default (`background` false), what side effects `sapper auto` has on the repositories, or that `skip_permissions` bypasses approvals.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with the operating model front-loaded and the hard requirement last; no filler. It is arguably over-compressed for a 12-parameter tool, but every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the deadline/round structure is covered. Still, for a 12-parameter, long-running orchestration tool with zero annotation coverage, the definition omits superset behaviors (background execution, permission bypass, per-step timeout, templates) that an agent needs to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% across 12 parameters, so the description must compensate and largely does not. It adds real meaning for `minutes_per` (per-round budget), `root` (scope of graphs) and the require-one-of relationship between `minutes` and `deadline`, but leaves eight parameters — `cwd`, `model`, `verify`, `max_steps`, `templates`, `background`, `exec_timeout`, `skip_permissions` — completely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete behavior: iterate over every challenge graph under `root`, give each `minutes_per` of `sapper auto` per round, repeat until the deadline. That is specific enough to distinguish it from a single-shot `sapper_auto` run. It stops short of 5 because the jargon ('round-robin driver', 'challenge graph') requires prior knowledge of the sapper model and it references `sapper sweep` rather than a sibling tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives one hard precondition — 'Requires minutes or deadline' — which prevents an invalid call. However, it never says when an agent should pick this over `sapper_auto`, `sapper_fleet`, or `sapper_dispatch`, nor when to avoid a long-running sweep; usage must be inferred from the round-robin framing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.