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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses a lot of behavior: parallel decomposition routing to 5,714 tools, the findings packet structure (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation), explicit gaps[] for unanswered facets, never-invented policy, semantic excerpting (not head-truncated), contradictions[] for standard/thorough, and expected latency ranges per depth. The caveat about citation_uri being present only when fetchable is especially transparent. No contradictions 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?

The description is long, but nearly every sentence earns its place by conveying operational behavior, constraints, and caveats that an agent needs for correct invocation. It is front-loaded with the most critical fact (account requirement and fallback). The main cost is the informal all-lowercase stylistic flourishes ('gaps[]', 'never invented'), which add personality but slightly reduce scannability. Given the complexity of the tool, the length is justifiable.

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 two well-documented parameters, no output schema, and rich annotations, the description covers the essential call conditions (auth, paid tier, fallback tool), expected latency, output format, edge-case behavior (unanswerable gaps, unresolvable citations), and the difference between depth levels. An agent has everything needed to select and invoke the tool correctly.

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?

The schema already documents both parameters fully (100% coverage), including the depth enum semantics. The description adds value by explaining what the depth values mean in terms of hops and contradiction passes and by elaborating that question can be broad/multi-part because decomposition is the point. This goes beyond the schema, though the schema itself did the heavy lifting — hence a 4 rather than 5.

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 'Grounded multi-source research across Pipeworx's 1495 STRUCTURED data sources... in ONE call' and explicitly contrasts with open-web search. The verb 'research' plus the resource (structured Pipeworx data sources) and the distinguishing scope ('broad/multi-part questions over structured data') clearly identify the tool's purpose. It even names the sibling 'ask_pipeworx' for single-lookup cases, so it is well differentiated.

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 first line gives an explicit account requirement and tells the agent to use ask_pipeworx instead when signed out. It then specifies when to use deep_research ('Best for broad/multi-part questions over structured data') and contrasts with 'For a single lookup use ask_pipeworx instead' — explicit when/when-not guidance plus named alternative.

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