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

Beyond annotations (readOnly, idempotent, non-destructive), the description discloses auth/licensing constraints, parallel decomposition across 5,724 tools, exact return-packet fields (verbatim evidence, confidence, source, fetched_at, citation, gaps[], contradictions[], hop, citation_uri), textual excerpting behavior, and latency. This substantially exceeds what structured annotations alone provide and does not contradict them.

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 dense and well-sequenced: account constraint first, then core function, routing guidance, depth mechanics, output details, and latency. A few points are repeated across the depth sentence and schema, and some details (e.g., 1,497 sources / 5,724 tools) are illustrative, but no part is filler; front-loading is strong.

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 has the full burden of explaining return values, and it does: findings packet structure, gaps[] for unanswered facets, contradictions[] for standard/thorough, hop and citation_uri semantics, and timing expectations. For a complex tool with 2 params and rich behavior, an agent has everything needed to decide and invoke 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 at 100% coverage, so the baseline is 3. The description goes further by tying depth to paid tiers ('depth:"thorough" needs a paid plan'), clarifying that question decomposition handles broad/multi-part input, and giving worked examples of acceptable questions. It adds operational meaning beyond the schema's parameter descriptions.

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 names a specific verb and resource: 'Grounded multi-source research across Pipeworx's 1497 STRUCTURED data sources' and contrasts it explicitly with 'NOT open-web search'. It also gives concrete example questions and lists what the return packet contains, so an agent can distinguish deep_research from ask_pipeworx and other siblings without inspecting 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?

It gives explicit routing rules: use ask_pipeworx when signed out, for a single lookup, or for breaking/colloquial current-news topics; use deep_research for broad/multi-part questions over structured data. It even explains why ('deep_research returns mostly empty gaps[]' for topics outside the catalog), which is decision-grade guidance.

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