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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered without the description. The description adds value beyond that: explicit latency expectations (15-60s, up to ~90s for thorough), the gaps[] never-invented behavior, the contradiction[] scan for standard/thorough, and the semantically-excerpted records. It doesn't explicitly state that citations are only present when fetchable, but it does convey the retrieval semantics. The only minor gap is that it doesn't describe the return format as a JSON structure, but since output schema is absent, the description covers the main behaviors well. Not a 5 because it omits explicit note of idempotency or the exact fields of the findings packet (verbatim evidence, confidence, source, fetched_at, citation).

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 information-dense but relatively long. Most sentences earn their place—latency, depth semantics, gaps, citations, exclusions, alternatives. However, there is some rambling and redundancy ('this is NOT open-web search' appears both early and later in the form of 'prefer ask_pipeworx...' etc.), and the middle section is verbose. It's front-loaded with the account requirement, but the structure could be tightened. A 3 is fair—not a model of conciseness.

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?

For a tool with 2 params, no output schema, and rich annotations, the description covers nearly everything an agent needs: what it returns, what it doesn't do (never invents), latency, auth requirements (account + paid for thorough), depth meanings, and distinguishing from siblings. It lacks an explicit statement that the result is a findings packet with a specific structure, though it enumerates the fields. It also doesn't mention error conditions or what happens with insolubly ambiguous questions, but those are minor for a research tool. Near complete.

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 description coverage is 100%, so the schema already documents both parameters well. The description adds value by explaining what 'depth' means in terms of facets and hops, which goes beyond the enum names, and by explaining the default behavior. It reinforces the 'question' parameter's intention. Slight redundancy but adds semantic color.

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 is explicit: it states a specific verb (researches), a specific resource (Pipeworx's 1517 structured data sources), and a distinctive mechanism (decomposes into facets, routes to 5,798 tools in parallel). It also explicitly distinguishes itself from open-web search and names sibling alternatives (ask_pipeworx). This is the strongest form of purpose clarity.

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 clear when-to-use guidance ('best for broad/multi-part questions over structured data'), explicit alternatives ('use ask_pipeworx instead' for unsigned users or single lookups), and mentions the exclusion (not open-web search). It also explains when to use depth levels. This is comprehensive.

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