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

With annotations already marking readOnly, openWorld, idempotent, and non-destructive behavior, the description still adds substantial behavioral context: account/auth requirements, parallelism, latency expectations ('15-60s' and 'up to ~90s'), the findings packet structure, gap reporting, contradiction detection, and no-invention guarantees. It also clarifies that citations are only included when actually fetchable, which is meaningful trust guidance 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 long but every sentence carries non-redundant, decision-relevant information: auth, scope, use cases, alternatives, depth semantics, output structure, citation guarantees, excerpting behavior, and latency. It is structured as dense prose rather than scannable bullets, which hurts readability modestly, but the content is consistently valuable and not padded.

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?

This is a complex orchestrator tool with no output schema, so the description carries the full burden of explaining what an agent should expect back. It covers the findings packet, per-finding fields (verbatim evidence, confidence, source, fetched_at, citation, hop), gaps[], contradictions[], citation resolvability, and performance expectations. This is effectively complete for a tool of this complexity.

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 thoroughly. The description adds extra meaning by detailing how depth levels behave beyond the enum labels, such as 'standard' re-angling unanswered facets and 'thorough' chasing leads in a second hop, plus the contradictions[] scan. It also clarifies that the question parameter should be natural language and that decomposition is intentional.

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 states the tool's function: 'Grounded multi-source research across Pipeworx's 1497 STRUCTURED data sources... in ONE call' with a specific process of decomposing questions into facets and routing them in parallel. It explicitly distinguishes itself from 'open-web search' and contrasts with sibling tools like ask_pipeworx, so an agent can tell exactly what this tool does and does not do.

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 provides explicit when-to-use and when-not-to-use guidance: 'Best for broad/multi-part questions over structured data' and 'For a single lookup use ask_pipeworx.' It also gives a concrete exclusion for breaking/current-news topics, saying 'prefer ask_pipeworx' because deep_research returns lingering gaps. Even the no-sign-in fallback is covered with 'If you are not signed in, use ask_pipeworx instead.'

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