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

Beyond the readOnly/idempotent annotations, the description discloses account requirements, latency (15-60s, up to ~90s for thorough), return-packet contents (verbatim evidence, confidence, source, fetched_at, citation_uri), the explicit gaps[] contract ('never invented'), contradictions[] behavior, and semantic excerpting of large records. This is rich, non-obvious behavioral context.

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 every section adds necessary context for a complex tool with no output schema: auth, alternatives, core mechanism, return fields, depth behavior, citation guarantees, and latency. It is front-loaded with the account requirement and alternative routing, though the prose is denser than needed in the middle.

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 high-complexity tool with no output schema, the description is exceptionally complete: it explains what the tool returns, how findings are sourced, what gaps and contradictions mean, how citations are guaranteed fetchable, which depth to choose, what to expect on latency, and when to use a sibling instead. An agent has enough to invoke and interpret results 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?

Input schema coverage is 100%, so the baseline is 3; the description adds value beyond the schema by tying depth levels to paid plans, latency expectations, gap recovery, and contradiction detection. It also provides concrete example questions, reinforcing that 'question' accepts broad, multi-part natural language.

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 verb ('research') and resource ('Pipeworx's 1517 STRUCTURED data sources'), and clearly differentiates from siblings by saying 'this is NOT open-web search' and contrasting with ask_pipeworx for single lookups. It also indicates this is for broad/multi-part questions, which is a sharper scope than a generic research tool.

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 routing guidance: use ask_pipeworx if not signed in or for a single lookup, and use deep_research for broad/multi-part structured-data questions. It also notes the paid requirement for depth:'thorough', telling the agent when a specific parameter value is unavailable.

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