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

Despite readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, the description carries far beyond annotations: account/tier gating ("depth:'thorough' needs a paid plan"), latency windows ("Expect 15-60s (thorough ... up to ~90s)"), the never-fabricates guarantee ("explicit gaps[] ... never invented"), semantic excerpting ("not head-truncated"), resolvable citation_uri behavior, and the breaking-news limitation yielding empty gaps[]. None of this is derivable from 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?

Every sentence earns its place — auth gate, fallback routing, core mechanism, caps/limitations, depth semantics, return packet, latency, citation resolvability. It is appropriately sized for a highly complex tool and front-loaded with the critical account requirement before anything else. Minor structural deduction: it is a single dense wall of text with no paragraph breaks or list formatting, and the depth behaviors are partially restated from the schema.

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 shoulders the burden of explaining return values — findings packet fields (verbatim evidence, confidence, source, fetched_at, pipeworx:// citation, hop, citation_uri, gaps[], contradictions[]) are all enumerated. It also covers auth/signup URL, paid tiers, latency, error/edge behavior (breaking news → mostly empty gaps), and sibling routing. For a tool with this complexity (2 params, 3 depth modes, massive parallel routing, no output schema), nothing decision-relevant 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% (both params fully documented), so baseline is 3. The description adds genuine value beyond the schema: the paid-plan gate tied to depth, per-depth latency expectations, and prose clarification that "standard" recovers gaps while "thorough" chases first-pass leads. The question param needs no elaboration since it explicitly accepts natural-language multi-part input.

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 and resource: "Grounded multi-source research across Pipeworx's 1497 STRUCTURED data sources ... in ONE call," with concrete mechanism (decomposes into facets, routes to 5,724 tools in parallel) and return format. It explicitly differentiates from siblings: "this is NOT open-web search" and contrasts with ask_pipeworx ('For a single lookup use ask_pipeworx (one LLM call, not many)').

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?

Gives explicit when/when-not conditions and names alternatives: "If you are not signed in, use ask_pipeworx instead — it works on every tier," "Best for broad/multi-part questions over structured data," and "For BREAKING or colloquial CURRENT-NEWS ... prefer ask_pipeworx — it routes to live news APIs; deep_research returns mostly empty gaps[]." The conditions map directly to tool selection.

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