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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavioral context beyond that: account/tier gating, latency expectations (15-60s, thorough up to ~90s), the gaps[] honesty guarantee ('never invented'), the contradictions[] pass for standard/thorough, the semantic excerpting behavior (not head-truncated), and the resolvable citation_uri guarantee. This is far richer behavioral disclosure than the annotations alone provide, with no contradiction.

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 (~250 words) but dense and front-loaded: the most operationally critical fact (ACCOUNT REQUIRED) opens the text, followed by the fallback alternative. The structure flows logically from what → how → when → depth mechanics → return format → latency. Some redundancy exists with the schema's depth descriptions and the caps-lock emphasis ('IN PARALLEL', 'IN ONE call') adds noise, but every sentence carries distinct information for a genuinely complex tool.

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 return-format burden and satisfies it: findings packet composition (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation), gaps[] for unanswered facets, contradictions[] for standard/thorough, hop field, and citation_uri resolvability. Auth requirements, tier gating, latency, sibling routing, and parameter nuances are all covered. Nothing an agent needs to call 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 description coverage is 100%, so the baseline is 3. The description adds value above the schema by explaining what each depth level does behaviorally (standard re-angles unanswered gaps; thorough chases leads from the first pass), which depth requires payment, and gives example questions that illustrate the 'question' parameter's intended granularity. It doesn't fully restate the schema but meaningfully elaborates the depth semantics beyond the enum descriptions.

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 names a specific verb+resource: 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources' that 'Decomposes your question into focused facets, routes each to the right one of 5,798 tools IN PARALLEL.' It explicitly differentiates from open-web search ('this is NOT open-web search') and from ask_pipeworx ('For a single lookup use ask_pipeworx instead'), so an agent can distinguish it from siblings without opening any 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?

Provides explicit when-to-use and when-not-to-use guidance: 'If you are not signed in, use ask_pipeworx instead — it works on every tier,' 'For a single lookup use ask_pipeworx instead,' and 'Best for broad/multi-part questions over structured data' with concrete example queries. The alternative tool is named and the selecting condition is stated, 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.