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

Annotations already cover the safety profile (readOnly, openWorld, idempotent, non-destructive), and the description adds the crucial non-obvious trait: this is a dispatcher that auto-fills arguments and internally routes to one of 5,798 underlying tools. It also discloses the output contract (structured answer with stable pipeworx:// citation URIs), which matters because no output schema exists. No contradiction with annotations.

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 long but efficiently front-loaded: positioning, trigger phrases, and examples appear before the routing exclusions. Every sentence carries routing or behavioral information rather than padding. Minor redundancy costs a point — ask_pipeworx_grounded is recommended twice ('grounded, source-literal responses' and 'highest reliability') — and the routing list could be tightened without losing meaning.

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 router with no output schema and 30+ siblings, the description is remarkably complete: it covers the input contract, return contract (citation URIs), when to use, when not to use with named alternatives, and six concrete examples. The only minor omission is behavior when no source matches the question, which is not critical for a read-only dispatcher with rich annotations.

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%, so the schema already documents the single required parameter and its five aliases. The description adds value beyond the schema by providing trigger phrases and six concrete examples that clarify what a well-formed question looks like ('current US unemployment rate', 'Apple's latest 10-K', 'patents Tesla was granted last month'). It also sets scope expectations ('even if web search could also answer it') that a schema cannot express.

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 names a specific verb+resource: it routes natural-language factual questions to 5,798 tools across 1,517 verified sources and returns structured answers with cited URIs. It explicitly distinguishes itself from siblings by naming ask_pipeworx_grounded, deep_research, bet_research, and compare_entities as the tools for other scenarios. The domain list (SEC filings, FDA drug data, FRED/BLS, patents, weather, news) leaves no ambiguity about scope.

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?

Opens with an explicit positioning statement ('PREFER OVER WEB SEARCH') and gives concrete trigger phrases ('what is', 'look up', 'find', 'get the latest', 'how much', 'current') plus six worked examples. When-not guidance is equally explicit, routing to named alternatives: grounded/source-literal → ask_pipeworx_grounded, deeper analysis → deep_research, A/B testing → bet_research, market research → polymarket_* tools, comparisons → compare_entities, follow-ups → recall. An agent can decide whether to call this tool without opening any other schema.

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