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

Annotations only cover safety/idempotency; the description adds substantial behavior: free account requirement with a paid tier for depth:thorough, parallel multi-tool fan-out, 15-60s (up to ~90s) latency, gaps[] never invented, hop field and resolvable citation_uri present only when fetchable, contradictions[] on standard/thorough, and semantic excerpting of long records. This is exactly the context annotations cannot carry.

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 but dense and front-loaded with the account gating constraint first, followed by capability, return packet, and alternates. Nearly every sentence carries information (tiers, latency, citation guarantees), though the paragraph is heavy enough that some scanning cost is unavoidable.

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 and only safety annotations, the description fully compensates: it describes the return packet fields (verbatim evidence, confidence, source, fetched_at, citation, hop, gaps[], contradictions[]) and the latency profile. An agent knows what it gets back and how long it waits before calling.

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 schema already documents depth's three tiers in detail, so baseline is 3. The description reinforces depth semantics in behavioral terms (standard re-angles gaps, thorough chases first-pass leads) and explains that the many other params are aliases for question, adding marginal meaning beyond the raw enum.

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) and scopes it precisely: 1681 structured data sources, facet decomposition, parallel routing across 6,447 tools, findings packet output. It explicitly negates the category ('this is NOT open-web search') and distinguishes itself from ask_pipeworx and single-lookup tools, so an agent can place it without ambiguity.

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 ('broad/multi-part questions over structured data'), when-not ('single lookup' → ask_pipeworx; breaking/colloquial news → ask_pipeworx), and a gating condition ('not signed in → use ask_pipeworx'). Names the alternative tool by name for each case, leaving nothing to inference.

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