nlq_query

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

Annotations already declare readOnlyHint=true and openWorldHint=true, establishing the tool as a safe read operation. The description adds that it returns 'structured ServiceNow data' via the NLQ API, but it does not disclose additional behavioral traits such as potential result format variability, response size limits, or that the NLQ may be interpreted in an open-world context. With annotations covering safety, the added value is moderate 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?

The description is a single concise sentence that immediately states the tool's purpose without wasted words. It is front-loaded with the core action ('Ask a natural language question') and result ('get structured ServiceNow data'). It loses a point for not including any additional context that would aid in selecting or invoking the tool, but it remains efficient.

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 read-only tool with three well-documented parameters and no output schema, the description provides the essential function but omits details about the response structure or any limitations of the NLQ API. Given that the tool is straightforward and annotations cover safety, the minimal description is adequate but not comprehensive. It could benefit from a note about the type of data returned or how results are structured.

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 input schema provides full descriptions for all three parameters (question, limit, table), achieving 100% coverage. The description does not add any parameter-specific meaning beyond what the schema already contains. The phrase 'natural language question' aligns with the 'question' parameter but does not elaborate on syntax or edge cases, so it meets the baseline without surpassing it.

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: 'Ask a natural language question and get structured ServiceNow data.' It specifies the NLQ API, which identifies the mechanism. However, it does not explicitly distinguish itself from sibling tools like natural_language_search, which may perform a similar function, so it falls short of a 5.

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 provides no guidance on when to use this tool versus alternatives such as natural_language_search or query_records. It only states what the tool does, leaving the agent without context for choosing among similar NLQ-based tools. No exclusions or alternative suggestions are mentioned.

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