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

Even with annotations (readOnlyHint, openWorldHint, idempotentHint), the description adds substantial behavioral context: it decomposes questions into facets, routes in parallel across 5,798 tools, returns gaps[] instead of inventing answers, performs gap-recovery hops for standard/thorough, returns contradictions[] for deeper tiers, uses semantic excerpting rather than head-truncation, and clarifies citation_uri resolvability. It also discloses latency expectations and plan/authentication requirements. No contradiction with annotations; in fact it enriches them.

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 and front-loaded with the critical account prerequisite, which is good. However, its length is considerable and parts are dense/compressed, such as the run-on sentence about citation_uri and hop fields, and the middle section about second-hop iteration could be clearer. Every sentence contributes, but structure could be improved for scanning. A 3 feels right: appropriately detailed but not highly polished.

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 research tool with no output schema, the description covers what matters: supported inputs, depth tiers with behavior, output composition (findings packet, gaps[], contradictions[], citations), error/latency expectations, and the negative case where gaps appear for off-catalog topics. It routes to alternatives when appropriate. Given the tool's complexity, this is remarkably 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 coverage is 100%, so the schema already documents both parameters well, and the depth enum descriptions in the schema are detailed. The tool description adds practical context for depth (e.g., 'thorough needs paid plan') and clarifies what a single lookup should use instead. The description doesn't re-explain the question parameter heavily, but the schema plus the contextual 'broad/multi-part' guidance covers it. A 4 is warranted because the depth parameter gains pricing and hop-count semantics beyond the schema's enum text.

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 ('researches'), a precise resource (Pipeworx's 1517 structured data sources), and a behavioral differentiator (multi-source, parallel decomposition, not open-web search). It explicitly contrasts with ask_pipeworx and open-web search, so an agent can distinguish it from siblings without inspecting schemas.

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 guidance: best for broad/multi-part structured-data questions, and explicitly says to use ask_pipeworx instead for single lookups, breaking news, or open-web/current-events questions. It also mentions the sign-in/paid-tier prerequisite and the fallback behavior when not signed in. This is strong routing guidance.

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