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

With no annotations, the description carries the behavioral burden. It discloses that matching is case-insensitive and returns up to 50 rows, which is useful. However, it does not mention return format, ordering, behavior when no rows match, or whether all columns are searched. This is adequate but not rich.

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 zero fluff. It front-loads the core action and the most important qualifiers (case-insensitive, any cell, limit). Efficient and to the point.

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?

For a simple search tool with two parameters, the description covers the essential behavior: what it returns, how matching works, and the result cap. It lacks explicit mention of result ordering or pagination, but given the low complexity and absence of an output schema, it is nearly complete. Siblings like dataset_stats or dataset_top require more context, but this search tool is adequately described.

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 schema covers the 'query' parameter with a description ('text to look for in any cell') and limit has no description. The tool description adds 'case-insensitive' and 'any cell', which extends schema meaning. But it does not elaborate on the limit parameter beyond the implicit 'up to 50'. With 50% schema coverage, it partially compensates but leaves limit semantics to the schema's bounds.

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 a specific verb (search) and resource (dataset rows), and adds the key detail that matching is case-insensitive and applies to any cell. It distinguishes itself from siblings like dataset_row (which fetches a specific row) and dataset_stats (which summarizes).

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 when to use it (to find rows containing a text query) but does not explicitly state alternatives or exclusions. It does not say 'use this instead of dataset_row when...' or mention when not to use it. The purpose is clear enough that an agent can infer usage, but explicit routing is absent.

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