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

Annotations already mark readOnly/openWorld/idempotent, but the description adds substantial extra behavioral context: latency expectations (15-60s, up to ~90s for thorough), the findings-packet structure (verbatim evidence, confidence, source, fetched_at, stable citations), honest gap reporting (gaps[], contradictions[], 'never invented'), and semantic excerpting rather than head-truncation. Also discloses auth/pricing constraints (free account required; thorough needs a paid plan), which annotations cannot express.

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?

Every sentence carries real information with zero filler, but the packaging is weak: it is one unbroken wall of text with poor front-loading (ALL-CAPS 'ACCOUNT REQUIRED' notice precedes the core function, and the ask_pipeworx fallback advice appears twice). Some constructions, such as the contradictions[] sentence, are syntactically tangled and force an agent to re-parse.

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 carries the full burden of explaining return values, and it does so thoroughly: findings-packet composition, citation semantics, gaps[] for unanswered facets, contradictions[] at standard/thorough, and excerpting behavior. Combined with auth, latency, and depth-tier coverage, an agent has everything it needs to invoke and correctly interpret the response.

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% — both question and depth are already documented, including enum meanings — so the baseline is 3. The description adds practical meaning on top by mapping tiers to behavior ('single hop' vs 'full iterative hop'), latency, and the paid-plan threshold. No additional syntax is needed for the natural-language question parameter.

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?

Names a specific verb+resource ('grounded multi-source research across Pipeworx's 1540 STRUCTURED data sources... in ONE call') and explains the mechanism (facets routed in parallel to 5,908 tools). Explicitly frames what it is not ('this is NOT open-web search') so it cannot be confused with a generic web-search tool, and provides concrete example questions.

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 an explicit best-for condition ('Best for broad/multi-part questions over structured data') with examples, and the counter-case ('For a single lookup use ask_pipeworx'). Also adds an auth-based routing rule ('If you are not signed in, use ask_pipeworx instead — it works on every tier'), fully spelling out when this tool is and is not the right choice.

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