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

Annotations already declare readOnly/openWorld/idempotent, and the description adds substantial disclosure beyond them: the findings-packet shape (verbatim evidence + confidence + source + fetched_at + stable pipeworx:// citation), a 'never invented' gaps[] guarantee, contradictions[] behavior for standard/thorough, semantic excerpting (not head-truncated), latency bounds (15-60s, ~90s for thorough), and paid-tier restrictions. No contradiction with 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 front-loads the critical account caveat and every sentence carries information, but at roughly 300 words it is overlong, and the passage 'Main bottleneck (one LLM call, not many)...' reads like a corrupted fragment that duplicates what the schema's depth enum description already says. Depth-tier facts are scattered across three separate spots, weakening the structure.

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?

With no output schema, the description must carry the return contract, and it does thoroughly: findings-packet fields, citation fetchability guarantee, gaps[], contradictions[], excerpting behavior, tier differences, and expected latency. For a tool this complex (multi-tier depth, permissions, non-trivial return shape), nothing an agent needs to decide whether and how to call it 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%, so the schema documents question and depth well. The description adds value on top: example question phrasings, the paid-plan consequence of depth='thorough', and per-tier behavioral details (gap-recovery hop, contradiction scan) that reinforce the enum semantics rather than merely repeating them.

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 Pipeworx's 1517 STRUCTURED data sources' in ONE call, and explicitly differentiates itself with 'this is NOT open-web search.' It also names the closest sibling (ask_pipeworx) as the single-lookup alternative, so an agent can select it without opening any 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 routing rules: 'If you are not signed in, use ask_pipeworx instead' and 'For a single lookup use ask_pipeworx instead.' It defines the ideal use case ('best for broad/multi-part questions over structured data') with two concrete example questions, leaving no ambiguity about when this tool wins over its siblings.

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