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

Annotations already declare readOnly=true, idempotent=true, destructive=false, openWorld=true, so the core safety profile is covered. The description genuinely adds beyond that — 15-60s latency (up to ~90s for thorough), auth/tier gating, gaps[] never invented, contradictions[] flags, semantic excerpting of long records, and a hop field — but the citation_uri sentence is convoluted and the paid-tier behavior is only implied. Strong add-on value, with some opacity remaining.

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?

The access precondition is front-loaded and every clause carries information, but the prose is a dense ~350-word run-on with recurring parentheticals and duplication of the standard/thorough semantics between description and the depth enum. It could be trimmed by a quarter without loss.

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 bears full burden for returns and does so: findings packet contents (verbatim evidence, confidence, source, fetched_at, citation), gaps[], contradictions[], and per-finding hop. Latency and failure mode (empty gaps when off-catalog) are also covered — nothing an agent needs 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 enum carries facet counts and hop structure, so the schema does the heavy lifting. The description still contributes by explaining the practical consequence of depth (gap recovery vs. lead chasing vs. contradictions scan) and by flagging that the seven alias parameters all map to question.

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 1857 structured data sources — and explicitly negates the closest misreading ("this is NOT open-web search"). It distinguishes itself from ask_pipeworx by scope (multi-facet, parallel fan-out vs. single lookup).

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?

Explicit when-to-use (broad/multi-part questions over structured data, with two concrete examples), when-not (single lookup, breaking/colloquial news), and the alternative (ask_pipeworx, described as working on every tier). Also documents the account and paid-tier prerequisite up front.

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