Sapper Pick

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

No annotations are provided, so the description carries the full behavioral burden. It does not say whether picking mutates state (for example, whether an intent is reserved or marked picked), what "next" means as a selection order, whether the store path must already exist, or how the claim/worker options affect side effects. Only the bare notion of selection comes through.

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?

One short sentence with no filler, and the core action is front-loaded. It is not verbose, but the brevity comes from under-specification rather than economy of expression.

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 no explanation. But this is a stateful, store-backed selection operation with four parameters and zero annotations, and the single sentence explains none of the state effects, ordering, or sibling relationship. For this complexity, the description leaves significant gaps an agent must guess at.

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 description coverage is 75%, so the schema explains most parameters, including claim, worker, and any_open. The description adds no parameter meaning at all: it does not explain the interplay between claim and worker, or what any_open includes. The baseline of 3 is appropriate because the schema does the work, but nothing extra is contributed.

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 gives a concrete verb and resource: "pick the next intent to work." But "intent" is domain jargon, and the parenthetical "(like `sapper pick`)" only repeats the tool name. It never distinguishes this from close siblings such as sapper_claim, sapper_brainstorm_pick, or sapper_frontier, so an agent cannot confidently choose between them from the text alone.

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 guidance is the shallow pointer "like `sapper pick`", which tells the agent nothing about when to use this instead of the sibling tools. There is no statement about prerequisites (initialized store, ready intents), ordering behavior, or exclusions, so any choice between sapper_pick and its siblings has to be inferred from other tools' definitions.

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