discover_rows

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

The description provides extensive behavioral details beyond annotations: it explains the pipeline (planner -> search -> QC -> pending_rows), the source label, the cost estimate mode, and that discovered rows land in pending_rows. This exceeds the not read-only, not destructive, open-world hints provided by annotations.

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 clear sections, front-loading the core action. It is slightly verbose with pipeline details but remains efficient and readable. Each sentence adds relevant information.

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 complexity of the tool (AI-powered discovery pipeline), the description is comprehensive. It covers prerequisites (validated table), workflow steps, output (pending_rows), and next steps (add_validated_rows). The presence of an output schema (though not shown) reduces the need for return value details.

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?

All four parameters are described in the input schema with 100% coverage. The description adds context by explaining the role of session_id (from a completed validation), instruction (natural language request), count (target number), and confirmed (triggers vs quotes). This adds value but is not essential given schema descriptions.

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's purpose: 'Discover and add new rows to an existing validated table using AI-powered search.' It specifies the resource (rows), action (discover/add), and method (AI-powered search). This distinguishes it from siblings like add_validated_rows (which validates pending rows) and get_results (which retrieves data).

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 explains when to use the tool (to discover new rows via AI) and outlines the two modes (confirmed=False for cost estimate, confirmed=True to enqueue). It mentions the dependency on a completed validation session and points to add_validated_rows for subsequent validation. However, it does not explicitly state when not to use it or list all alternatives.

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