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

Annotations already mark this as read-only, open-world, idempotent, and non-destructive, so the baseline bar for additional context is high. The description nonetheless adds rich behavioral detail: parallel decomposition into 5,798 tools, findings packet structure (verbatim evidence + confidence + source + fetched_at + citation), gaps[] for unanswered facets, contradictions[] for standard/thorough, latency expectations (15-60s, thorough ~90s), and 'never invented' honesty about gaps. It also carefully explains citation behavior and how large records are excerpted semantically. 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 information-dense and front-loaded with the most important operational constraints (account required, use ask_pipeworx if not signed in). However, it is quite long and contains some awkward/unclear text including the garbled parenthetical 'depth:"thorough" needs a paid plan' and a confusing string of words in the middle ('one LLM call, not many'). While every sentence carries useful content, the density and slight incoherence make it less digestible. A tighter rewrite would score higher.

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 complex tool with two parameters, no output schema, and significant behavioral nuance, the description covers the essential operational context: account/auth prerequisites, speed expectations, how the tool differs from alternatives, what the output contains, failure/gap behavior, and precautions against assuming invented findings. Nothing critical is left out for an agent deciding whether and how to invoke it.

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 baseline is 3, but the description adds substantial meaning beyond the schema: it explains what the depth values actually do (quick=3 facets single-hop, standard=default with gap-recovery + contradictions, thorough=6 paid with iterative hop), and clarifies the question parameter accepts broad/multi-part natural language because 'decomposition is the point.' That is meaningful added semantics, not schema repetition.

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 opens with a clear verb+resource: 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources... in ONE call.' It explicitly distinguishes itself from open-web search and names the sibling alternative (ask_pipeworx). The purpose is unmistakable and well differentiated.

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') and when-not-to-use ('For a single lookup use ask_pipeworx'). It also states an account requirement and which depth tier needs a paid plan. This is ideal routing guidance for an agent.

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