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

Annotations (readOnlyHint, openWorldHint, idempotentHint) cover safety, but the description adds far more: account/pricing tiers, 15-90s latency windows, findings-packet fields, gaps[] never-invented semantics, contradictions[] on standard/thorough, semantic excerpting instead of head-truncation, and resolvable citation_uri guarantees. The 'NOT open-web search' scoping usefully qualifies the openWorldHint rather than contradicting it.

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: account gate, routing rules, mechanism, output packet, sibling exclusion, depth behavior, citations, timing. It is well front-loaded with the auth requirement and fallback routing. The only deduction is presentational — it is a single dense wall-of-text paragraph that would be more scannable with breaks or bullets, though an LLM parser tolerates this well.

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 must carry the full return-value burden, and it does: verbatim evidence, confidence, source, fetched_at, pipeworx:// citation, gaps[], contradictions[], hop field, and citation_uri fetchability are all enumerated. Auth, pricing, latency, and edge behavior (empty gaps on out-of-catalog topics) are covered. Nothing an agent needs to call this 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% and the depth enum already carries granular hop semantics, so baseline is 3. The description adds genuinely useful meaning beyond the schema: thorough requires a paid plan (operationally critical), latency varies by depth (15-60s, thorough up to ~90s), and the behavioral difference between one-hop quick vs iterative multi-hop standard/thorough — all value the schema alone doesn't convey.

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 1,540 STRUCTURED data sources via parallel decomposition and routing to 5,908 sub-tools, returning a findings packet. Explicitly distinguishes itself from open-web search and names what it is NOT, making it easily separable from siblings.

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/when-not and alternative routing: 'Best for broad/multi-part questions over structured data', 'For a single lookup use ask_pipeworx', 'For BREAKING/CURRENT-NEWS topics, prefer ask_pipeworx', and a hard auth gate ('If you are not signed in, use ask_pipeworx'). The agent is told exactly when to select this tool versus alternatives.

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