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

With no annotations, the description carries full responsibility for behavior. It discloses case-insensitive matching, matching across any cell, and a hard cap of 50 results. It stops short of stating default limit behavior, sorting, or empty-result behavior, but the core operational traits are present.

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?

A single sentence with no wasted words. The result type (Rows of the dataset) is front-loaded, followed by the matching condition, case sensitivity, and limit in a natural, scannable order.

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?

The core purpose and constraints are clear enough for a simple two-parameter search tool, but the optional limit has no stated default and there is no mention of what happens when no rows match or what the returned row structure contains. These gaps matter for an agent deciding how to invoke it correctly.

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 only 50%, covering query but not limit. The description compensates by clarifying that query is searched case-insensitively across cells and that limit represents an upper bound of 50 returned rows, adding meaning beyond the schema's bare numeric constraints.

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 rows of the ProbeLedger dataset whose cells contain the query. The case-insensitivity and 50-row cap further refine the scope, distinguishing it from sibling tools like dataset_stats or dataset_columns which serve different lookup purposes.

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 no explicit guidance about when to use this tool versus alternatives. The described behavior implies it is for content-based row search, but no when-to-use conditions or exclusions are stated, leaving the agent to infer the selection criteria.

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