notebook_run_pipeline

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

No annotations are provided, so the description carries the full burden. It discloses that the tool runs cells in notebook order, optionally saves outputs back to the file (save_outputs), stops on error (stop_on_error), and uses a specified kernel. It does not mention any destructive actions beyond saving outputs, which is explicitly controlled by a parameter.

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 description is well-structured with a brief introductory sentence, a note on setting tags, a sibling tool reference, and a clear 'Args:' section. It is efficient, but could be slightly more condensed without losing clarity. Still, it earns its sentences and is front-loaded.

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?

Given the tool's complexity (6 parameters, 2 required) and the presence of an output schema, the description is fairly complete. It explains all parameters, the execution order, and provides a pointer to a related tool. It does not cover return values, but that is acceptable since an output schema exists. Minor gaps like error handling beyond stop_on_error are covered by the parameter description.

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?

The input schema has 0% description coverage, so the tool description compensates fully. It provides clear, meaningful explanations for all six parameters, including defaults (e.g., 'Kernel to use (default: 'python3')') and behavior ('Stop at first failing cell (default: true)'). This adds essential context beyond the schema alone.

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 clearly states 'Run all cells tagged with a pipeline stage, in notebook order.' It specifies the verb (run), resource (cells tagged with a stage), and behavior (order). It also explains how to set tags and distinguishes itself from siblings like notebook_run_all and notebook_run_cell.

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 description provides explicit guidance to 'Use notebook_list_stages to see what stages exist in a notebook,' indicating when to use this tool versus that alternative. It does not explicitly state when not to use the tool, but the sibling context and the detailed parameter explanations imply appropriate usage.

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