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

Annotations already declare read-only/open-world/idempotent, lowering the bar, and the description clears it easily: never-invented gaps[], resolvable citation_uri only when fetchable, contradictions[] for standard/thorough, semantic excerpting (not head-truncated), a hop field per finding, and concrete latency expectations (15-60s, ~90s for thorough). This is substantial behavioral context beyond the annotations, with no contradiction.

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?

Dense and well front-loaded: the account gate and core purpose land in the first two sentences, and nearly every sentence adds new information. Docked for a redundant stray fragment ('(one LLM call, not many)') that repeats 'in ONE call', and the ask_pipeworx routing advice appears three separate times, which slightly blunts the structure.

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 carries the full burden of explaining return values, and it does so thoroughly: findings packet fields (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation), gaps[], contradictions[], hop, and citation_uri semantics. Auth requirements, tier gating, latency, data coverage, and alternatives are all covered. For a tool this complex, nothing essential 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 description is already rich (facet counts, default, hop behavior, contradictions scan), so the baseline is 3. The description adds real value on top: thorough being paid, the gap-recovery vs. lead-chasing difference across depths, and latency consequences of each depth — all of which inform parameter choice. Not a 5 because the schema already carries most of the depth semantics.

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 1540 STRUCTURED data sources') plus the mechanism (facets routed to 5,908 tools in parallel) and an explicit negative scope ('this is NOT open-web search'). It also names its nearest sibling as what it is not, so an agent can distinguish it from ask_pipeworx and its other 30 siblings without opening any schema.

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-to-use ('Best for broad/multi-part questions over structured data'), when-not-to-use ('For a single lookup use ask_pipeworx instead'), and a hard precondition ('If you are not signed in, use ask_pipeworx instead'). It even routes a specific edge case (breaking/colloquial/current-news topics) to the alternative and states that depth:'thorough' requires a paid plan. 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.