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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description layers on rich behavioral context annotations cannot carry: the account/paid-plan auth requirement, 15-90s latency, the gaps[] never-invented guarantee, contradictions[] only for standard/thorough, the citation_uri fetchability promise, and semantic excerpting of large records. No conflict with 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 (~400 words) but every sentence earns its place: auth and the sibling fallback are front-loaded, and the depth semantics, output shape, and failure modes are dense with no filler. Slightly run-on in places, but justifiable for a tool with two enum values and multi-hop behavior.

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?

With no output schema, the description carries the full burden of return-value disclosure and delivers: findings packet fields (verbatim evidence, confidence, source, fetched_at), gaps[], contradictions[], the hop field, and citation_uri semantics. Combined with 100% schema coverage and readOnly annotations, nothing an agent needs to select or invoke the tool 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% and the depth enum is already well-documented, so baseline is 3; the description adds value by mapping each depth value to observable behavior — 'depth:"standard" re-angles unanswered gaps', 'thorough additionally chases the best leads', and which tiers return contradictions[]. It also flags the paid-plan gate for thorough, which the schema notes but the description reinforces.

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+resource: 'Grounded multi-source research across Pipeworx's 1499 STRUCTURED data sources... in ONE call', and explicitly distances itself from open-web search. It also names ask_pipeworx as the single-lookup alternative, further pinning down what deep_research is for and distinguishing it from siblings.

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?

Explicit when/when-not guidance: 'If you are not signed in, use ask_pipeworx instead', 'For a single lookup use ask_pipeworx', and 'deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog'. It also marks the tool as best for broad/multi-part questions over structured data with concrete examples, leaving nothing to inference.

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