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

The description discloses key runtime behavior: case-insensitive substring matching across all cells, and a result cap of 50. It does not mention error handling or return format, but given the absence of annotations, the description carries the burden and does so reasonably.

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 a single sentence, directly to the point, with the key information (query matching, case-insensitivity, limit) front-loaded. No unnecessary words or redundancy.

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 simple nature of a search tool with no output schema or annotations, the description provides sufficient context: what it returns (rows), how matches occur, and the result limit. It does not need to explain return field details or error scenarios for this simplicity level.

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 tool description adds minimal meaning beyond the schema: it reiterates query matching and explicitly states the result cap of 50, which clarifies limit's purpose. However, it does not explain default values or edge cases for either parameter, and the schema's limit parameter lacks a description.

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 that the tool returns rows from the dataset where any cell contains the query, with case-insensitive matching and a limit of 50. This distinguishes it from sibling tools like dataset_row (single row), dataset_stats (aggregates), and dataset_top (top rows).

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 implies usage for text-based searching, but it does not explicitly contrast with sibling tools or state when not to use it. There is no mention of alternatives or exclusions, so guidance is only implicit.

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