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

Annotations already declare readOnlyHint=true and idempotentHint=true; the description adds the behavioral specifics that matter most: it decomposes the question into facets, routes to tools in parallel, returns verbatim evidence with confidence/source/fetched_at/citation, returns explicit gaps[] for unanswered facets, never invents answers, re-angles gaps on second hops, returns contradictions[] for standard/thorough, excerpted (not head-truncated) records, and expected latency 15-90s. It also explains the citation_uri is present only when fetchable. This is rich behavioral disclosure well beyond annotations.

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 description is dense and every sentence adds value, but it is long and somewhat rambling, mixing account requirements, routing logic, hop semantics, citation mechanics, and latency into a single paragraph. It front-loads the account gate effectively, yet the structure could be tightened with short labeled segments rather than a wall of prose. Still, little is wasted.

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?

Given the tool's high complexity (2 params, one enum, no output schema), the description covers the essential operational facts: prerequisites/auth, paid tier, expected latency, output packet shape, gap/contradiction semantics, citation resolvability, and when the tool will fail. An agent has everything needed to decide whether and how to invoke it. The output schema is absent, but the description compensates by enumerating the return fields (verbatim evidence, confidence, source, fetched_at, gaps, contradictions).

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 genuine semantic value by explaining the practical meaning of depth values: 'standard' adds gap-recovery hop + contradictions scan, 'thorough' is paid and adds iterative lead-chasing; it also clarifies that 'quick' is single-hop. It does not repeat the schema, and it makes the enum selection meaningfully easier. Slight shortfall for not giving an explicit 'when to pick standard vs thorough' example, but still above baseline.

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 ('research'), a precise resource (Pipeworx's 1517 structured data sources, routed across 5,798 tools), and explicitly distinguishes itself from open-web search and from ask_pipeworx. It also gives example questions, so an agent can confidently select this tool over its 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?

The description gives explicit when-to-use conditions ('best for broad/multi-part questions over structured data'), explicit when-not-to-use conditions (breaking news / open-web topics → 'mostly empty gaps[]'), and names the alternative tool (ask_pipeworx) including the account-tier condition. This is unusually complete routing guidance.

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