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

Annotations already declare readOnly/openWorld/idempotent, and the description adds substantial context beyond them: the GitHub sign-in and paid-tier auth requirements, latency expectations (15-60s, thorough up to ~90s), the 'never invented' guarantee via gaps[], contradiction detection on standard/thorough, semantic excerpting rather than head-truncation, and the guarantee that returned citation_uris are always resolvable. There is no contradiction — readOnlyHint is consistent with a research-and-return tool, and openWorldHint matches the explicit unknown-handling behavior.

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 front-loaded with the critical failure condition (ACCOUNT REQUIRED), which is good structure. However, the block 'Best for broad/multi-part questions ... use ask_pipeworx — it works on every tier' is duplicated verbatim, and 'it works on every tier' also reappears in the opening sentence. The content is dense and mostly earns its place, but the redundancy is an editing defect that adds noise.

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 correctly takes on the burden of explaining return values: the findings packet fields (verbatim evidence, confidence, source, fetched_at, pipeworx:// citation), gaps[], contradictions[], hop, and citation_uri behavior are all described. Auth prerequisites, latency, what the tool will not do, and when to pick a sibling are all covered. Everything an agent needs to invoke the tool and interpret its result is present.

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 schema already documents both parameters thoroughly, including the full depth enum semantics (quick=3, standard=3 with gap-recovery + contradictions, thorough=6 with iterative hop + paid flag). The description's added value for parameters is thin: latency expectations per depth and a restatement of the paid-tier constraint already present in the schema. Baseline 3 is appropriate since the schema carries the semantic load.

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 1500 STRUCTURED data sources ... in ONE call', with a concrete mechanism (decompose into facets, route in parallel). It actively distinguishes itself from siblings: 'this is NOT open-web search' and names ask_pipeworx as the alternative for single lookups. The 'Best for broad/multi-part questions over structured data' line pins its intended use precisely.

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?

Explicitly conditions usage on a concrete state: 'If you are not signed in, use ask_pipeworx instead — it works on every tier.' It also contrasts with the sibling for the alternative case: 'For a single lookup use ask_pipeworx.' Example questions are given to illustrate when it applies, and the paid-tier boundary (depth:'thorough') is disclosed up front.

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