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

Annotations only convey read-only/open-world/idempotent traits. The description goes far beyond: facet decomposition, parallel routing across 5,743 tools, findings-packet structure (verbatim evidence, confidence, source, fetched_at, stable citation), the never-invented gaps[] guarantee, contradictions[] on standard/thorough, semantic excerpting of long records, resolvable citation_uri with hop field, and latency expectations. No contradiction with annotations; the safe-read profile is reinforced by the described behavior.

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?

Long (~250 words) but dense with non-redundant operational information for a tool with no output schema, so the length is mostly earned. The gating account requirement is front-loaded before the purpose statement, a defensible ordering for agent decision-making. Minor redundancy with the depth enum description prevents a 5.

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 burden of explaining return semantics — and it delivers: findings packet fields, gaps[] and contradictions[] behavior, citation fetchability, and excerpting. Auth requirements, tier gating, timing, and explicit routing to alternatives are all present. Nothing an agent needs to invoke 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%, so the baseline is 3. The description adds genuinely new operational context: depth='thorough' requires a paid plan, and expected latency per tier (15-60s, up to ~90s for thorough). However, the hop-recovery semantics for standard/thorough are largely restated from the schema's depth enum description, which is redundant and keeps this from a 5.

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 and resource: 'Grounded multi-source research across Pipeworx's 1500 STRUCTURED data sources' with concrete catalog examples (SEC, FRED/BLS, FDA, USPTO). The explicit 'NOT open-web search' disclaimer plus example questions like 'compare X and Y's regulatory + financial exposure' make the scope and distinction from siblings unmistakable.

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?

Names ask_pipeworx as the alternative under three distinct conditions: not signed in ('works on every tier'), single lookup, and open-web/news topics ('prefer ask_pipeworx — it routes to live news APIs'). It states its own best-fit condition ('broad/multi-part questions over structured data'), so an agent knows exactly when to select this tool versus any sibling.

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