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

The description goes far beyond the readOnly/openWorld/idempotent annotations by disclosing the parallel decomposition, the findings-packet shape (verbatim evidence, confidence, source, fetched_at, citation), explicit gaps[] with no fabrication, the hop field, resolvable citation_uri, contradictions[], semantic excerpting, and expected latency. It even flags the paid tier for depth:'thorough'. Nothing contradicts 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 operational information: auth, alternatives, output format, citation guarantees, timing, and depth behavior. It is front-loaded with the most decision-critical constraint (account required) and uses bold and explicit contrasts to keep the structure navigable. Minor redundancy around contradictions and the paid tier keeps it from a 5.

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 no output schema, the description is remarkably complete: it explains what the agent will receive (findings packet, gaps, contradictions, hop, citation_uri), how long the call takes, which depth values cost money, and what types of queries will fail (breaking news). An agent has enough context to invoke it correctly and interpret the response.

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 behavioral meaning beyond the enum definitions: it explains the gap-recovery hop, the lead-chasing behavior of 'thorough', the contradictions[] scan, and the paid-plan requirement for 'thorough'. The question parameter is already well-described in the schema, so the description's added value is mainly on depth semantics.

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 specific verb and resource: "Grounded multi-source research across Pipeworx's 1500 STRUCTURED data sources." It clearly distinguishes itself from open-web search and from sibling ask_pipeworx by describing the decomposition-and-parallel-tool-routing behavior. The examples ('compare X and Y's regulatory + financial exposure') further anchor what the tool is for.

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?

Explicit guidance is given for when to use deep_research ('Best for broad/multi-part questions over structured data') and when not to ('For a single lookup use ask_pipeworx', 'For BREAKING or colloquial CURRENT-NEWS ... prefer ask_pipeworx'). It also names the account prerequisite and the fallback tool if not signed in, leaving no ambiguity about selection.

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