orchestrator_next_action

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

With no annotations, the description carries the full burden and does well: it discloses the gating/refusal behavior, the meaning of done=True, and that submit requires human approval. It offers no detail on permissions beyond the options check, but the disclosed refusal semantics are exactly the kind of behavioral trait that matters here.

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?

Three tight sentences, front-loaded with the return payload before the gating caveats. No padding, and the most important behavior (refusal condition) is present without burying the purpose.

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-value explanation is not required, and the description covers purpose, the done sentinel, and the options-check precondition. For a two-parameter orchestration tool this is largely complete, with only the app_dir meaning left unaddressed.

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 0%, so the description must compensate. It explains the non-obvious parameter (skip_options_check bypasses the options-confirmed gate), which is valuable, but app_dir is never described. Partial compensation warrants a mid score.

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 concretely what the tool returns for a 'driver loop': a stage, subagent role, retry budget, and instructions. This is a specific verb+resource outcome, not a restatement of the name. It does not, however, differentiate itself from adjacent siblings like pipeline_next or orchestrator_preflight.

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 genuine preconditions — it refuses until run options are confirmed unless skip_options_check=true, and notes setup_required comes first — which implies a correct call order. It stops short of saying when to prefer this over pipeline_next or orchestrator_preflight, so usage is implied rather than explicit.

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