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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true. The description adds significant behavioral context: it states what happens if not signed in, that it never invents gaps[], that citations are resolvable only when the source emits one, that large records are semantically excerpted, that contradictions[] are returned for standard/thorough, and that latency is expected (15-60s, up to ~90s for thorough). It also discloses parallel tool routing (5,798 tools) and the gap-recovery/lead-chasing iterations. No contradiction with 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 long but information-dense; nearly every sentence adds a distinct fact (sign-in requirement, alternative tool, source scope, mechanism, output contents, gap handling, citation resolvability, latency). It is front-loaded with the most operationally critical information (account requirement and fallback). It loses one point for being somewhat sprawling and parenthetical-heavy, but it earns its length given the tool's complexity.

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 a rich input schema and no output schema, the description is remarkably complete: it covers failure mode (gaps[]), citation behavior (always fetchable, with caveat), latency, depth variants, contradictions, excerpting, and alternatives. An agent can decide whether to call this tool, how to phrase the question, which depth to choose, and what to expect in the response. The lack of an output schema is compensated by the detailed findings-packet description.

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 thoroughly. The description adds meaningful semantics beyond the schema: it explains how depth values map to facets/hops ('quick=3 (single hop)', 'standard=...gap-recovery hop...', 'thorough=6...iterative hop'), and clarifies the meaning of 'broad/multi-part is fine' for the question parameter. It doesn't merely repeat schema 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 clear resource ('Pipeworx's 1517 STRUCTURED data sources'), and explicitly distinguishes itself from open-web search. It also names the sibling alternative (ask_pipeworx) for signed-out users. The scope is precise: broad/multi-part questions over structured data, with a one-call decomposition-and-parallel-routing behavior.

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 questions over structured data'), explicit when-not-to-use/sign-in guidance ('If you are not signed in, use ask_pipeworx instead'), and names the alternative tool directly. It also contrasts with open-web search. Depth levels are explained in the schema and reinforced in the description with timing and behavioral differences.

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