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

Annotations already carry the safety profile (readOnly, non-destructive, idempotent, open-world), and the description goes far beyond them: auth requirements, latency windows (15-60s, up to ~90s for thorough), the never-invents guarantee via explicit gaps[], citation fetchability (citation_uri present only when resolvable), multi-hop iteration behavior, contradictions[] scanning, and semantic excerpting of large records. 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?

Long but unusually dense — nearly every sentence carries a distinct operational fact (auth, fallback, scope, mechanism, output format, latency, citation guarantee, excerpting), and the most critical constraints (account required, use ask_pipeworx if not signed in) are front-loaded ahead of the purpose statement. Not a 5 only because some internal mechanics (the 5,798 parallel tools, hop field details) could be trimmed without losing agent-relevant guidance.

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 multi-hop tool with no output schema, the description is fully self-sufficient: it specifies the return format (verbatim evidence + confidence + source + fetched_at + citation_uri), gap and contradiction handling, iteration depth per tier, latency, prerequisites, and the fallback sibling. Nothing an agent needs to select, invoke, or interpret the result is missing.

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% and the depth enum description is already rich (quick/standard/thorough semantics, paid flag), so the baseline is 3. The description adds real value above that: practical depth behavior (re-angles unanswered gaps, chases best leads), the paid-plan gate tied to 'thorough', and question-shape guidance with examples. Not a 5 because the schema already does the heavy lifting for both 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?

States a specific verb+resource: grounded multi-source research across 1,517 structured data sources with a clear mechanism (facet decomposition, parallel routing to 5,798 tools, findings packet). Explicitly distinguishes itself from siblings ('this is NOT open-web search', 'For a single lookup use ask_pipeworx instead'), so an agent can tell it apart without opening the schema.

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?

Gives explicit when-to-use guidance ('Best for broad/multi-part questions over structured data') with two concrete worked examples, and names the alternative tool (ask_pipeworx) under two distinct conditions: not signed in, and single-lookup questions. Also discloses prerequisites up front: GitHub sign-in required, thorough depth needs a paid plan.

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