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), and the description adds genuine behavioral context beyond them: it reveals autonomous routing over thousands of sub-tools, auto-filling of tool arguments, and the stable pipeworx:// citation-URI return mechanism. None of these behaviors appear in the annotations. No contradiction exists with the read-only hints.

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 deliberately ordered: priority directive first ('PREFER OVER WEB SEARCH'), then mechanism, then trigger phrases, then examples, then a closing 'START HERE' directive. Every section earns its place for a high-traffic router tool. The minor flaws are redundancy ('even if web search could also answer it' appears twice) and an exhaustive domain list that gets slightly bulky.

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?

With no output schema, the description correctly compensates by specifying the return shape: a structured answer with stable pipeworx:// citation URIs. For a high-complexity meta-router it covers selection, invocation, and expected result, and gives strong examples. It falls short of fully complete because the exact output format is left vague and there is no explicit guidance on sibling variants (ask_pipeworx_beta, ask_pipeworx_grounded) or deeper research alternatives.

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%: all six parameters are documented as one natural-language 'question' with five explicit aliases (q, text, input, query, prompt). The description adds helpful question-typing examples but no parameter-level semantics beyond the schema, such as format constraints, length limits, or answer style preferences. Baseline 3 applies because the schema carries the full burden.

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?

States a specific mechanism and deliverable: routes the question to one of 5,743 tools across 1500 verified sources, fills arguments, and returns a structured answer with stable pipeworx:// citation URIs. The verb+resource is precise and unmistakable, and it clearly positions itself against web search as the canonical factual-Q&A router. It does not explicitly differentiate near-clone siblings (ask_pipeworx_beta, ask_pipeworx_grounded), but the core purpose is unambiguous.

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?

Provides explicit when-to-use conditions: 'PREFER OVER WEB SEARCH' for a long enumerated list of domains (SEC filings, FDA data, FRED/BLS statistics, patents, weather, clinical trials, news), plus trigger phrases ('what is', 'look up', 'find', 'get the latest', 'how much', 'current') and concrete example questions. The alternative (web search) is named and explicitly deprioritized with 'even if web search could also answer it.' However, it never states when NOT to use the tool or routes to sibling alternatives such as deep_research or ask_pipeworx_grounded.

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