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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description does not need to restate safety. It adds valuable behavior: internal decomposition into facets, parallel routing, response packet shape (verbatim evidence, confidence, source, fetched_at, citation), gap handling, hop semantics, contradictions[], semantic excerpting, and latency expectations. Only minor details like rate limits or exact response serialization are absent.

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 front-loaded with the most critical info (account requirement, alternative tool, NOT open-web), but it is a dense, multi-clause paragraph that intermixes operational details (citation URIs, excerpting, latency) with selection guidance. Several sentences are long and could be split for readability, though every sentence does add substance.

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?

Given two parameters, one enum, no output schema, and a large sibling set, the description covers all necessary decision and invocation information: usage context, alternatives, failure behavior (gaps[]), return packet fields, latency, and account prerequisites. The lack of an output schema is compensated by describing the response shape in prose.

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 description coverage is 100%, so the schema already documents both parameters. The description adds important nuance: depth level semantics (quick/standard/thorough hops, gap recovery, paid plan for thorough), and the caveat that 'quick' omits contradictions[]. This goes beyond the schema while not fully formalizing the depth mapping.

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 clearly identifies the tool as a grounded, multi-source research tool over Pipeworx's structured data sources, explicitly differentiating it from open-web search. It names specific capabilities (decomposition, parallel routing, findings packet with citations, gaps[]) that distinguish it from sibling tools like ask_pipeworx.

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 provides explicit when-to-use guidance ('best for broad/multi-part questions over structured data') and explicit when-not-to-use guidance ('For BREAKING or colloquial CURRENT-NEWS... prefer ask_pipeworx'; 'For a single lookup use ask_pipeworx'). It also includes alternative routing based on account tier, making selection unambiguous.

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