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

The description adds substantial behavioral detail beyond the annotations: it explains decomposition into facets, parallel routing across 5,908 tools, the findings-packet structure, gaps[] for unanswered facets, no fabrication of answers, contradiction scans for deeper depths, latency expectations, and semantic excerpting of large records. This is rich, non-obvious, and useful behavioral context that annotations alone do not provide.

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 front-loaded with the most critical operational constraint (account requirement) and then organized around core behavior, return packet, best-use case, and alternatives. It is dense and mostly earns its length, though it is somewhat verbose and repeats the ask_pipeworx alternative more than necessary.

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 no output schema, the description is remarkably complete: it covers prerequisites, result shape, confidence/source/citation fields, gap handling, depth-specific behavior, timing, and exclusions. An agent has enough context to select and invoke the tool correctly and to set expectations about the result.

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, and the description adds extra meaning beyond the schema: it explains what broad/multi-part questions are suitable, defines each depth level's behavior in terms of hops and gap-recovery, and clarifies that thorough is paid. This helps an agent choose a correct value rather than just knowing the enum.

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 states a specific action — grounded multi-source research across Pipeworx's structured data sources in one call — and explicitly differentiates itself from open-web search and from ask_pipeworx for single lookups. It clearly names the resource, the behavior, and the scope, so an agent can distinguish deep_research from siblings without ambiguity.

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 gives explicit when-to-use and when-not-to-use guidance: it is best for broad/multi-part questions over structured data, ask_pipeworx should be used for single lookups, and ask_pipeworx is the fallback if the user is not signed in. It also includes account/tier requirements, so an agent knows prerequisites before invoking.

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