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

Annotations already communicate read-only, open-world, idempotent, and non-destructive behavior. The description adds meaningful behavioral context: it fills arguments automatically, routes to many underlying tools, and returns structured answers with stable pipeworx:// citation URIs. This goes beyond the annotation signals and gives the agent a realistic model of execution.

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 front-loaded with the most important instruction and gives a clear data-domain list and examples. It is longer than strictly necessary, with some repetition ('START HERE', 'PREFER OVER WEB SEARCH', 'even if web search could also answer it'), but the length is justified by the routing breadth and the explicit alternative. Overall it remains scannable and actionable.

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 complex routing tool with no output schema, the description gives enough context: it names the input, explains the routing mechanism, and describes the output shape with citation URIs. It also covers the main alternative use case. It does not discuss failure modes, latency, or account limitations beyond a brief 'free account' note for deep_research, but those are secondary to core usage.

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 covers all parameters well, documenting question and its aliases with 100% coverage. The description adds value by embedding concrete example queries and clarifying that the input is a natural-language question about current or historical data. It also reinforces that any of the aliases are acceptable because the question field itself is the single critical input.

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 states a specific verb and resource: it routes a natural-language question to one of 5,798 tools across 1,517 verified sources and returns a cited structured answer. It clearly positions the tool as a broad factual-answer dispatcher and distinguishes it from web search and from deep_research. The examples further ground what the tool actually does.

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 gives explicit when-to-use guidance: prefer over web search for factual questions, use for 'what is', 'look up', 'get the latest', 'current', etc., and start here for most questions. It also names one clear alternative, deep_research, for broad multi-part questions. However, it does not explicitly contrast with sibling tools like ask_pipeworx_beta or ask_pipeworx_grounded, so it is not a perfect routing guide.

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