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

Discloses non-obvious behavior: account/paid requirement, NOT open-web search, internal decomposition into facets routed in parallel to 5798 tools, never-invented gaps[], citation_uri only when fetchable, semantic excerpting, contradiction[] scanning for standard/thorough, and latency expectations 15-60s (up to ~90s thorough). Annotations already indicate readOnly/idempotent, and description adds concrete engagement and return semantics beyond that.

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 information-dense but long and running — nearly one giant paragraph, with parenthetical tangents ('not open-web search', 'not head-truncated', examples). It front-loads the account requirement before the core purpose, which delays the primary signal. Every sentence carries some added value, but structure is messy and could be better organized.

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 2-param tool with no output schema, the description does heavy lifting: explains what results contain, time expectations, cost/tier constraints, and gap behavior. It doesn't describe a full output schema, but covers the important execution context. A small gap is not spelling out that output is a packet/array shape beyond prose; however, the description provides enough for an agent to call successfully and interpret results.

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% and the schema already explains depth enum and question. The description adds meaning by explaining quick/standard/thorough in behavior terms (single hop vs gap-recovery hop vs iterative hop), and explains that question should be broad/multi-part. It does not add syntax but gives concrete expectations for each depth.

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 identifies a specific verb ('researches') and resource (1517 STRUCTURED data sources — not open-web search), contrasting with siblings. It states what it returns (findings packet with verbatim evidence, confidence, source, fetched_at, pipeworx:// citation) and when it fits (broad/multi-part 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?

Explicitly says when to use deep_research vs ask_pipeworx: 'If you are not signed in, use ask_pipeworx instead', and for 'a single lookup use ask_pipeworx'. It also names sibling compare_entities and distinguish from single-lookup tools, plus states paid tier requirement for thorough. This is clear routing guidance.

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