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

Annotations already cover readOnly/openWorld/idempotent/destructive safety, and the description adds a wealth of context beyond them: account/depth-tier cost, the never-invents guarantee, explicit gaps[] for unanswerable facets, contradictions[] at standard/thorough depth, semantic excerpting of long records, parallel routing to 5,767 tools, and 15-90s latency expectations. 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?

Long (~230 words) but every sentence is information-dense, and the highest-stakes operational facts (account requirement, fallback tool, NOT open-web search) are front-loaded. The citation/citation_uri and contradiction explanations are somewhat verbose, but each adds a fetchability or reliability guarantee that affects how an agent trusts results.

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?

There is no output schema, so the description compensates by specifying the return packet in detail: verbatim evidence + confidence + source + fetched_at + resolvable pipeworx:// citation, plus gaps[] for unanswered facets and contradictions[] for disagreeing findings. For a complex parallel-routing tool with paid tiers, everything needed to decide correct invocation is present.

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 question and depth thoroughly, including the quick/standard/thorough hop behavior. The description adds marginal value by noting 'thorough' requires a paid plan and gives latency expectations per depth, but most parameter semantics are already carried by the schema's enum 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?

Opens with the hard constraints and then states a specific verb+resource: 'Grounded multi-source research across Pipeworx's 1506 STRUCTURED data sources' and explicitly declares 'this is NOT open-web search.' It names the sibling alternative (ask_pipeworx) for the single-lookup case, so an agent can distinguish deep_research from siblings without opening their 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?

Gives explicit when-to-use guidance with examples: 'Best for broad/multi-part questions over structured data' followed by two concrete sample questions. It provides explicit exclusions ('For a single lookup use ask_pipeworx') and account-based routing ('If you are not signed in, use ask_pipeworx instead — it works on every tier'). Nothing is left to inference.

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