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

Annotations already mark the tool as read-only, open-world, idempotent, and non-destructive, so the description's burden is lower. The description still adds substantial behavioral context: account/paywall requirements, latency expectations, guarantee that gaps[] are never invented, citation_uri resolvability, hop/contradiction behavior, and semantic excerpting. This goes well beyond the 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 information-rich but quite long, with several parentheticals and repeated depth details already present in the schema. It front-loads account requirements and the key alternative, which is good, but the later latency and hop details could be tightened. Every clause adds some value, yet the overall structure is more sprawling than crisp.

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?

There is no output schema, so the description carries the full burden of explaining return values. It does this thoroughly: findings packet fields, confidence, source, fetched_at, citations, gaps[], contradictions[], hop, and citation_uri conditions. It also covers auth requirements, paid tiers, latency, and source scope. For a complex research tool, this is genuinely 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%, and the input schema already documents both `question` and the depth enum with detailed behavior for quick/standard/thorough. The description largely restates these points rather than adding new parameter-level meaning. It adds useful output-level context, but not much beyond what the schema already provides for parameters.

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 clearly identifies the tool as grounded multi-source research over Pipeworx's 1506 structured data sources, explicitly distinguishing it from open-web search and from ask_pipeworx. It states what the tool does with specific verbs: decomposes questions, routes facets to tools in parallel, and returns a findings packet. The contrast with siblings such as ask_pipeworx is explicit rather than implied.

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 routing guidance: use ask_pipeworx if not signed in, and use ask_pipeworx for single lookups. It also states that deep_research is best for broad/multi-part questions over structured data, with examples. This gives an agent clear decision criteria for when to invoke this tool versus a sibling.

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