Sapper Command

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

With no annotations supplied, the description carries the full burden, and it does disclose the most important trait: this is a long-running autonomous loop that only stops at a deadline or an explicit stop, and should be backgrounded for real use. It does not say what the loop mutates on disk, whether it spawns external LLM processes, what auth/permission needs it has (skip_permissions is never mentioned), or what a caller should expect while it runs.

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?

The purpose is front-loaded in the first clause and the whole definition is three short sentences with no padding. It is compact and scannable, though the brevity is a symptom of under-specification rather than disciplined economy.

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?

For a 16-parameter, unannotated autonomous orchestration loop, this is far too thin: it does not explain the interaction between minutes, timeout, deadline, minutes_max, minutes_default, exec_timeout, poll_seconds, and max_steps, nor the meaning of verify, templates, or fleet_file. The presence of an output schema excuses it from describing return values, but almost nothing else an agent needs in order to invoke it safely is covered.

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?

No parameters are documented in the schema (0% coverage across 16 parameters), so the description must compensate and largely fails: only `root`, `background`, and the deadline/stop concept are touched, while model, verify, minutes, timeout, max_steps, templates, fleet_file, poll_seconds, and skip_permissions are entirely unexplained. Two documented-but-vague concepts are not enough for a 16-parameter tool.

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?

It states an orchestration action ('LLM allocates the next work slice across per-challenge graphs under `root`') and frames it as a loop running until deadline/stop, which is more specific than a restated title. However, jargon like 'field commander loop' and 'work slice' is undefined, and nothing distinguishes it from siblings such as sapper_auto, sapper_fleet, or sapper_dispatch, so an agent cannot confidently choose between them.

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?

The only usage guidance is 'use background=True for real campaigns', which implies short/foreground runs are for trials, but this is left to inference. There is no statement of when this tool should be preferred over sibling orchestration tools, no prerequisites (e.g. init/setup state, permissions), and no when-not-to-use guidance.

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