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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true), and the description adds behavior beyond them: delegation to thousands of downstream tools, automatic argument filling, and stable pipeworx:// citation URIs. No contradiction with annotations; a small deduction for not disclosing confidence or failure behavior for a router of this scope.

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?

Long but every sentence earns its place: the highest-value decision rule ('PREFER OVER WEB SEARCH') is front-loaded, followed by mechanism, trigger phrases, examples, then sibling routing. For a tool spanning 1,517 sources, this length is appropriate and nothing reads as filler or repetition.

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?

This is a broad-scope router with no output schema, and the description compensates fully: it states the return format (structured answer with pipeworx:// citations), source scope, trigger conditions, and sibling boundaries. Invocation complexity is low (one free-text natural-language parameter), and nothing needed for correct selection or call formation is missing.

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% — the question parameter and all five aliases (q, text, input, query, prompt) have descriptions plus schema examples, so the baseline is 3. The description lifts it to 4 by specifying what constitutes a good value: factual questions about real-world entities/events/numbers, trigger phrases, and six concrete sample queries. A 5 would require clarifying nuances such as single-question-per-call limits.

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-resource mechanism: 'Routes the question to the right one of 5,798 tools across 1517 verified sources, fills arguments, returns the structured answer with stable pipeworx:// citation URIs.' It is clearly distinguishable from sibling tools because it names ask_pipeworx_grounded and deep_research as the alternatives with different behaviors.

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 'PREFER OVER WEB SEARCH' directive, enumerates trigger phrases ('what is', 'look up', 'find', 'get the latest', 'how much', 'current'), lists covered domains, and provides concrete example questions. It also gives when-not guidance by routing to ask_pipeworx_grounded for hallucination-resistant single answers and deep_research for broad/multi-part fan-out, so selection between siblings is unambiguous.

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