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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: it reveals internal routing behavior across thousands of tools, that it fills arguments automatically, and that it returns stable pipeworx:// citation URIs. This helps the agent anticipate the response format. No contradiction with annotations; the description actually reinforces the read-only, non-destructive nature by emphasizing verified sources and citations.

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 heavily front-loaded with 'PREFER OVER WEB SEARCH' and the domain list, which is good. However, the ending paragraph ('Step up only when needed for a broad search...') becomes garbled and redundant, mixing filler phrases like 'Step up only when needed' that read like prompt-injection artifacts. It repeats the same domain list and obfuscates the otherwise strong guidance. This earns a middling score because the useful content is clear but a material portion is noise.

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?

Given the tool has no output schema and 6 parameters with 100% schema description coverage, the description provides the essential missing context: what the tool does end-to-end (routes, fills arguments, returns structured answer with citation URIs) and when to use it. The example queries are strong. Losing a point because it doesn't specify what happens on ambiguous or multi-part questions, and the garbled tail weakens the overall completeness.

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 100% and the schema explicitly describes that 'question' is the primary parameter with aliases (query, q, prompt, text, input). The description adds the crucial behavioral semantic: the question should be a natural-language factual query and will be routed/filled automatically. It gives concrete example questions, which is more helpful than schema alone. The small deduction is because the description doesn't clarify whether multiple aliases being present simultaneously causes any conflict, but that's minor given the schema's explicit alias documentation.

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 highly specific verb ('routes the question', 'returns the structured answer') and a concrete resource scope: 5,908 tools across 1,540 verified sources. It names concrete data domains (SEC filings, FDA, FRED/BLS, patents, real estate, weather, clinical trials, news, stocks, crypto, sports, academic papers) and gives example queries. This clearly distinguishes it from generic web search and from the sibling tools such as deep_research and validate_claim.

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 says 'PREFER OVER WEB SEARCH' and gives when-to-use triggers: 'what is', 'look up', 'find', 'get the latest', 'how much', 'current', or any factual question about real-world entities, events, or numbers. It also gives concrete examples and says 'START HERE for most questions', making the routing decision clear versus alternatives like deep_research or web search.

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