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

Annotations already carry readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the bar is lower; the description adds substantial context beyond them: account/auth prerequisite with a paid-tier gate, latency expectations (15-60s, thorough ~90s), the gaps[] never-invented guarantee, semantic excerpting of large records, hop-field semantics, contradictions[] for standard/thorough, and citation_uri resolvability. No contradiction with annotations — readOnly matches the read-only research nature.

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 carries load — account requirements, use-case boundaries, depth semantics, timing, output guarantees — with zero filler. However, it is a dense single wall of text that leads with account prerequisites rather than the core purpose (which arrives third), and it runs long relative to typical definitions. The length is justified by the tool's complexity, so this is not overspecification, just a minor front-loading flaw.

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 fully carries the return-value burden and does so: it details the findings packet (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation), gaps[], contradictions[], hop field, and citation_uri fetchability. It also covers auth, depth choice, timing, and exclusions. For a complex 2-param tool with rich annotations, nothing an agent needs to invoke it correctly 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 baseline is 3. The description adds real meaning beyond the schema: it maps each depth enum value to behavioral outcomes (quick=3 facets single hop, standard=3 with gap-recovery hop + contradictions scan, thorough=6 with iterative lead-chasing), which the schema's enum text only partially conveys. It also clarifies the question parameter accepts broad/multi-part input since decomposition is the point. This exceeds the baseline but isn't maximal.

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+resource: 'Grounded multi-source research across Pipeworx's 1543 STRUCTURED data sources' in ONE call, explicitly flagging 'this is NOT open-web search.' It differentiates from the sibling ask_pipeworx by naming the exact boundary ('For a single lookup use ask_pipeworx') and the tool's decomposition/routing mechanism, so an agent can select it unambiguously.

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?

Exceptionally explicit: names the alternative (ask_pipeworx) with the conditions that select it ('if you are not signed in', 'single lookup', 'BREAKING or colloquial CURRENT-NEWS'), states what it is best for (broad/multi-part over structured data), and gives per-depth usage semantics (quick/standard/thorough with hop behavior). Nothing is left to inference.

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