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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds substantial behavior beyond them: account and paid-tier gating for 'thorough', latency expectations (15-60s, up to ~90s), parallel facet decomposition, gaps[] never invented, hop and citation_uri fields with resolvability guarantees, contradictions[] for standard/thorough, and semantic (non-head-truncated) excerpting. 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?

Critical information is front-loaded (auth gate first, then core mechanism, then routing guidance) and every substantive point earns its place. However, the description is visibly redundant: the ask_pipeworx routing guidance and the 'empty gaps[]' warning appear nearly verbatim twice, and an orphaned fragment '(one LLM call, not many)' disrupts flow. A tighter edit would preserve all information in roughly 25% less text.

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 covers everything an agent needs: return packet structure (verbatim evidence, confidence, source, fetched_at, citation), gap/contradiction behavior, hop semantics, citation resolvability, latency, auth requirements, depth-tier differences, and explicit disambiguation from ask_pipeworx. There is no material gap in what an agent must know to invoke it correctly and interpret results.

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; both params are already documented. The description adds real value on top: it explains the tier gating ('thorough' needs a paid plan), elaborates the depth semantics in prose (standard re-angles gaps, thorough chases leads from the first pass), and gives worked examples of what makes a good 'question'. This justifies one point above baseline.

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 mechanism: 'Grounded multi-source research across Pipeworx's 1500 STRUCTURED data sources... Decomposes your question into focused facets, routes each to the right one of 5,743 tools IN PARALLEL' and returns a defined findings packet. It explicitly differentiates from siblings ('this is NOT open-web search', 'ask_pipeworx... routes to live news APIs'), so an agent can distinguish it without opening schemas.

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?

Usage conditions are explicit and actionable: 'If you are not signed in, use ask_pipeworx instead', 'Best for broad/multi-part questions over structured data', and 'For a single lookup use ask_pipeworx' / 'For BREAKING or colloquial CURRENT-NEWS topics, prefer ask_pipeworx'. The description even tells the agent what failure mode to expect (empty gaps[]) when misapplied to non-catalog topics.

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