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

Annotations already declare readOnly, openWorld, and idempotent behavior, but the description adds substantial non-obvious context: account/paywall requirements, expected latency, the gaps[] and contradictions[] fields, guarantee that findings are never invented, fetchability semantics for citations, and semantic excerpting behavior. This goes well beyond annotation coverage and contains no contradictions.

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 densely informative, with critical routing and account information front-loaded. Some redundancies exist — the paid-plan requirement for 'thorough' is stated twice, and the caveat-heavy prose could be tightened — but nearly every sentence contributes a distinct behavioral fact.

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 tool with no output schema, the description is remarkably complete: it covers output structure (findings packet with verbatim evidence, confidence, source, fetched_at, pipeworx:// citation), gaps[] behavior, contradictions[], latency expectations, authentication requirements, and the exact distinction from sibling tools. Nothing essential for correct invocation 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?

Although schema coverage is 100%, the description adds meaningful depth semantics for the 'depth' enum — describing quick/standard/thorough in terms of facets, hops, gap recovery, contradiction scanning, and paywall status. It also clarifies that 'question' accepts broad natural-language questions and that decomposition is intentional.

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, distinctive function: grounded multi-source research across 1,517 structured data sources, with decomposition into facets and parallel routing. It explicitly contrasts itself with open-web search and names ask_pipeworx as the alternative for single lookups, making sibling differentiation immediate and 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?

It gives clear when-to-use guidance: best for broad/multi-part questions over structured data, citing concrete example questions. It also states explicit exclusions and alternatives — use ask_pipeworx when not signed in or for single lookups — so an agent can route correctly without guessing.

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