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

With no annotations, the description carries the full burden. It mentions case-insensitivity and a row cap, but omits key behavioral details: whether results are ordered, what happens if no rows match, whether the search is substring or token-based, and whether it scans all columns. These gaps are material for an agent deciding on invocation.

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, compact sentence that front-loads the core behavior. It is appropriately brief, though it sacrifices detail for brevity. It earns a 4 for being tight and readable, but it lacks the structure to include important qualifiers.

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 search tool with no output schema and no annotations, the description is incomplete. It does not specify result ordering, empty-result behavior, pagination, or error handling. It also fails to indicate whether the search is substring or whole-word, which could change the agent's expectations. Given the tool's simplicity, more contextual detail is needed.

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 50% (only query has a description). The description repeats the query purpose ('contain the query') but adds nothing about the limit parameter beyond an implicit 'up to 50', which is already in the schema as a maximum. It does not explain how limit controls the result size or what its default is, so the description fails to compensate for the missing schema 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 the tool's function: returning rows of a dataset that contain a given query, case-insensitively, capped at 50. It is specific and distinct from sibling tools like dataset_row (single row) or dataset_stats (statistics).

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?

No guidance is provided on when to use this tool versus alternatives. It does not mention that this is the tool for full-text searching, nor does it exclude other dataset tools for different operations. The description is purely functional with no usage context.

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