pipeline.run_dag

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

No annotations provided, so description must disclose behavior. It describes the DAG execution, return types, and the optional edge-integration loop with self-stopping. Lacks details on side effects, permissions, or resource consumption, but covers key operational modes.

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?

Information is packed into a single dense paragraph. Some redundancy like 'default_visualization=True (default)' could be simplified. Structured bullet points or separate sections would improve readability for a complex tool.

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 14 parameters, no output schema, and no annotations, the description is insufficient. It omits descriptions for most required inputs and doesn't clarify return format beyond output names. A complete description would explain each parameter's role and expected values.

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 description must add meaning. It explains iterative_integration, integration_params (with sub-parameters), and default_visualization, but ignores 11 out of 14 parameters (e.g., session_id, positive_control_genes, ppi_edges). Most required params lack any semantic explanation.

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 the tool runs the full fail-closed DAG for a session and returns specific outputs (negative_result_report or target_handoff). It distinguishes itself from siblings by describing iterative vs single-shot modes, which links to integration.convergence_check sibling.

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?

Provides guidance on when to use iterative_integration=True vs single-shot, and mentions default_visualization behavior. However, it lacks explicit when-not-to-use scenarios or comparisons with sibling tools like boolean.augment_compare or metabolic.simulate.

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