search_datasets

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the returned fields (dataset ids, name, description, keywords, status), the status-preference guidance, the large corpus size (over 1,600 datasets), and the TS-prefix naming convention for census tables. It does not mention pagination or limits, but this is a search tool with no side effects and an output schema already supplies the return structure.

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 organized into three concise paragraphs: purpose, returned data, and search guidance. Every sentence contributes practical information, and the main purpose is front-loaded. It is slightly longer than strictly necessary but remains focused and easy to parse.

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 single-parameter search tool with an output schema, the description is remarkably complete. It tells the agent exactly what to search, how to phrase the search, which results to prefer, what the return will contain, and how to proceed to the next tool. No essential call-time information is missing.

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 already describes the query parameter thoroughly with field-targeting prefix syntax and bare-term behavior at 100% coverage. The description goes beyond the schema by adding practical guidance: prefer narrow terms, use 'TS058' as an example, and understand that census summary tables use a TS prefix. This adds real value without being redundant.

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 opens with a specific, unambiguous statement: 'Find NOMIS datasets by keyword.' It names the exact resource (NOMIS datasets), the action (find by keyword), and distinguishes itself from the sibling get_dataset_dimensions by saying 'Start here, then call get_dataset_dimensions.' This is a clear, non-of-a-duplicative purpose.

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 explicitly tells the agent to start with this tool before calling get_dataset_dimensions, and provides a strong selection rule: prefer 'Current' status datasets over 'Historical' unless the user requested historical. It also advises using narrow search terms. It does not explicitly contrast with search_codes or fetch_data, but the resource-type distinction makes the primary use case obvious.

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