pipeline_next

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

With no annotations, the description carries the behavioral burden and does it well: it discloses the refusal/gating behavior, the skip_options_check escape hatch, and the ordered setup_required return. It does not state whether the call is read-only or has side effects, leaving a modest gap.

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 with the core behavior (return the next mandatory step) front-loaded, followed by the gating conditions. Every sentence adds a distinct constraint with no filler.

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 correctly omitted; the description instead covers prerequisites and ordering behavior, which is the right focus. Only the required app_dir parameter is left implicit.

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%, so the description must compensate. It usefully explains skip_options_check (skipping the options check) but says nothing about app_dir, which is the required parameter. Partial compensation for the coverage gap.

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?

States a specific verb and resource: returns the next mandatory step plus its instructions (driver). This is clearly distinct from pipeline_status and pipeline_mark, though it does not explicitly name a sibling to differentiate from. An agent can tell what it produces.

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?

Gives clear preconditions: it refuses until run options are confirmed via run_options/run_options_save, and returns setup_required first when AppFactory is not set up. This tells the agent when it will and won't function, though it stops short of explicitly routing to alternative tools.

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