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

Annotations (readOnlyHint=true, openWorldHint=true, idmpotentHint=true) already cover the safety profile; the description goes far beyond them with operational realities: account/paywall requirements, 15–60s latency (90s for thorough), gap recovery passes, contradictions[] behavior, semantic excerpting vs head-truncation, and the guarantee that citations are only emitted when resolvable ('never invented'). 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 every sentence carries load-bearing information: auth gate, fallback routing, scope, return packet shape, depth semantics, latency, citation guarantees, excerpting strategy. It is front-loaded with the account requirement. Slightly dense and could be split into structured paragraphs, but no filler.

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, slow, paid-tier tool with no output schema, the description fully compensates: it documents the return shape (findings packet with evidence/confidence/source/fetched_at/citation), gap handling, contradictions[], latency, auth, and fallback routing. Nothing an agent needs to correctly invoke and interpret this tool 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%, so the bar is a baseline 3, but the description adds real selection value: it ties each depth choice to concrete behavioral outcomes (number of passes, gap-recovery hops, contradictions scan, paid requirement, latency), and reinforces that natural-language multi-part questions decompose cleanly. This enriches how an agent would choose among quick/standard/thorough beyond the schema's enum text.

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 verb ('Grounded multi-source research'), a concrete resource scope ('1517 STRUCTURED data sources'), and hard differentiators: 'in ONE call — this is NOT open-web search.' The description far exceeds the generic title and positions the tool against ask_pipeworx and open-web search, so an agent can tell exactly what this tool is and is not.

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?

Explicitly names the alternative for unsigned-in users ('use ask_pipeworx instead — it works on every tier'), for single lookups ('For a single lookup use ask_pipeworx'), and states the best-fit use case ('broad/multi-part questions over structured data'). When-to-use and when-not-to-use are both spelled out.

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