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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds significant behavioral context beyond that: parallel decomposition across 5,767 tools, gap recovery hops per depth level, contradictions[] scanning, semantic excerpting, stable pipeworx:// citations, and expected latency (15-60s, up to ~90s for thorough). It does not explicitly restate the read-only behavior, but the annotations carry that; the cost/latency and iterative-hop behavior are genuinely additive.

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 dense and information-rich, but it is long and somewhat disorganized, with parenthetical asides and mid-sentence shifts (e.g., 'For a single lookup use ask_pipeworx...' embedded in the middle; the tier/latency details are crammed into the opening parenthetical). The most critical routing fact (not open-web search) is present early, but the paragraph could be restructured into clearer sections. Still, nearly every sentence earns its place—there is no fluff.

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-parameter tool with no output schema, the description covers the key things an agent needs: what the tool does, when to prefer it, what the findings packet contains, how depth levels differ, latency expectations, and auth requirements. It stops short of listing the exact output JSON shape, but with no output schema and a rich prose description, this is a reasonable completeness level. The slight deduction is for not mentioning pagination or how to handle partial results beyond gaps[].

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 parameters are already documented in the schema. The description adds value by explaining the practical trade-offs between depth levels in prose: quick=single hop, standard=3 facets with gap-recovery, thorough=6 paid with lead-chasing. It also clarifies that 'question' is meant to be broad/multi-part and that decomposition is the point, reinforcing the schema's natural-language guidance.

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 1506 STRUCTURED data sources'), and explicitly distinguishes itself from open-web search and from the sibling ask_pipeworx. It also names concrete use cases (broad/multi-part questions) and sibling alternatives, so an agent can differentiate it from the 30+ other tools without opening schemas.

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 guidance: use deep_research for broad/multi-part questions over structured data, and use ask_pipeworx for single lookups or when not signed in. It also contrasts with open-web search and clarifies tier prerequisites ('depth:thorough needs a paid plan'), which is actionable routing information.

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