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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, and the description is consistent with them (no contradiction). The description adds meaningful behavioral context beyond those flags: it reveals the tool is a router/aggregator that fills arguments from 5,743 tools, returns citation URIs, works on every tier, and is 'one fast call' — information that shapes an agent's expectations about cost and output.

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 dense and long (~150 words) but every sentence carries distinct information: preference over web search, capability, trigger signals, concrete examples, escalation paths, and tier availability. It is front-loaded with the highest-value guidance ('PREFER OVER WEB SEARCH') and the alternatives are logically grouped at the end; only slight trimming of overlapping examples would make it tighter.

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 tool with no output schema, the description covers the essentials: when to invoke it, what happens internally (routing, argument-filling), what the response includes (structured answer + citation URIs), and how it differs from its closest siblings. It stops slightly short of describing the response structure in more detail, but given the annotations already carry the safety profile and 'structured answer with citation URIs' is stated, it is complete enough for correct invocation.

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 description coverage is 100% — the schema already documents that all six parameters are aliases for a natural-language 'question'. The description enriches this with domain examples and phrasing triggers, but those largely overlap with the schema's own examples (e.g., questions about Apple revenue and bitcoin). The description adds marginal value over the schema without compensating for any coverage gap, so the baseline of 3 applies.

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 uses specific verbs and a clear resource: it 'Routes the question to the right one of 5,743 tools across 1500 verified sources' and 'returns the structured answer with stable pipeworx:// citation URIs'. It definitively positions itself as the general factual-question entry point and explicitly contrasts with ask_pipeworx_grounded and deep_research, so an agent can distinguish it from siblings without opening their schemas.

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?

Usage guidance is explicit and actionable: 'PREFER OVER WEB SEARCH', 'START HERE for most questions', and trigger phrases ('what is', 'look up', 'find', 'get the latest', 'how much', 'current') are listed. It also names alternatives with selection conditions — ask_pipeworx_grounded for hallucination-resistant single answers and deep_research for broad/multi-part fan-out — plus a breaking-news exception, so when-not-to-use is fully covered.

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