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

Annotations already carry readOnlyHint=true, openWorldHint=true, and idempotentHint=true, so the bar for added value is higher — and the description clears it substantially. It discloses that findings are grounded with verbatim evidence and confidence scores, that gaps[] are explicit and never invented, that citation_uris are only present when actually resolvable via resources/read, that standard/thorough include a contradictions[] scan, that large records are semantically excerpted rather than head-truncated, and that latency ranges from 15-60s up to ~90s. This is rich behavioral context well beyond the annotations, and nothing contradicts the read-only/open-world/idempotent hints.

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 (roughly 270 words) but nearly every sentence earns its place given the tool's complexity: auth, routing decision, scope, output shape, depth semantics, latency. It is front-loaded with the most consequential constraint (ACCOUNT REQUIRED). It loses a point for being a dense single wall of text with some redundancy between the prose depth explanation and the already-detailed schema enum description; light restructuring or trimming of the second-hop paragraph would make it a 5.

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?

There is no output schema, so the description correctly carries the full burden of explaining the findings-packet return shape — verbatim evidence, confidence, source, fetched_at, pipeworx:// citation, hop field, citation_uri resolvability, gaps[], contradictions[]. Combined with the annotations and a fully-documented input schema, there is no missing information an agent needs to decide whether to call this tool or to interpret its response.

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% for both parameters, so the baseline is 3. The description adds value beyond the schema by attaching behavioral consequences to depth — thorough costs money, thorough can take up to ~90s, quick is single-hop, standard/thorough do gap-recovery and contradictions[] — and by illustrating what makes a good question ('Broad/multi-part is fine — decomposition is the point' is schema, but the compare/regulatory examples are description). This exceeds the baseline slightly, so 4 is appropriate rather than 3.

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 and resource ('Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources... in ONE call') and clearly states the mechanism: decompose into facets, route to 5,798 tools in parallel, return a findings packet. It explicitly differentiates itself from open-web search and from ask_pipeworx, and gives concrete example questions. An agent can confidently distinguish this from every sibling without opening a schema.

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-to-use guidance is present: 'Best for broad/multi-part questions over structured data' with two worked examples. Alternatives are named with selection conditions: 'For a single lookup use ask_pipeworx' and 'If you are not signed in, use ask_pipeworx instead — it works on every tier.' The account/paid-plan prerequisite is stated up front, so an agent can route around auth failures.

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