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

Annotations already carry readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, and the description is fully consistent with these (research is a non-destructive read). Beyond the annotations it adds rich behavioral context: account/paywall requirements, latency expectations (15-60s, up to ~90s for thorough), the never-invented gaps[] guarantee, reproducible pipeworx:// citations, contradiction[] scanning, and passage-level semantic excerpting. This is substantial added value over structured fields.

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?

Front-loaded with the most actionable constraint (account required, paid tier for thorough) followed by sibling differentiation. The prose is dense and long, but nearly every sentence carries unique operational value — packet structure, citation resolvability, gap handling, latency. Minor deduction for sheer length; a wall of text for parsing agents, though nothing is wasted.

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 carries the full burden of explaining return values and does so thoroughly: findings packet with verbatim evidence + confidence + source + fetched_at + citeable URI, gaps[], hop field, and contradictions[]. Auth needs, latency, and sibling routing are all covered. Nothing an agent needs to invoke this correctly is missing.

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%, so both params are documented there (baseline 3). The description adds value beyond the schema: for 'question' it reassures 'Broad/multi-part is fine — decomposition is the point', and for 'depth' it explains the behavioral consequence of each level ('standard' re-angles unanswered gaps; 'thorough' additionally chases leads). This slightly exceeds the plain schema enum descriptions without fully re-documenting them.

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?

States a specific verb and resource ('Grounded multi-source research across Pipeworx's 1545 STRUCTURED data sources... in ONE call') and explicitly differentiates itself ('this is NOT open-web search'). It names sibling ask_pipeworx as the alternative for single lookups, so an agent can distinguish between them immediately. The scope ('broad/multi-part questions over structured data') is unmistakable.

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?

Provides explicit when-to-use ('Best for broad/multi-part questions over structured data') AND when-not-to-use ('For a single lookup use ask_pipeworx', 'For BREAKING or colloquial CURRENT-NEWS... prefer ask_pipeworx'). It names the alternative tool and the exact conditions that select it, leaving nothing to inference. The depth-tier semantics further tell the agent how to choose quick/standard/thorough.

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