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

Annotations already declare the tool safe (readOnly/openWorld/idempotent/non-destructive), and the description adds substantial behavioral context beyond that: account/paywall requirements, parallel decomposition mechanics, the 'never invented' guarantee via gaps[], contradictions[] scanning, resolvable citation_uri semantics, semantic excerpting of large records, and expected latency ranges per depth tier. No structured field conveys this behavior, and nothing contradicts the 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?

The description is long but front-loaded with the most decision-critical constraint (account required) and the sibling fallback, and every sentence carries distinct information — pricing, routing mechanics, output structure, citation behavior, timing. Slight redundancy exists with the schema's depth enum explanation, but for a tool with 2 params and no output schema, the density is justified.

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 explaining return semantics, and it does so comprehensively: findings packet composition (verbatim evidence, confidence, source, fetched_at, citation), gaps[], contradictions[], the hop field, and fetchable citation_uri guarantee. Combined with the account prerequisites and timing expectations, an agent has everything needed to invoke and interpret this tool correctly.

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% — both parameters have detailed descriptions, so baseline is 3. The description adds genuinely schema-external meaning: depth:'thorough' requires a paid plan, quick/standard/thorough map to hop behavior and latency (15-60s, ~90s for thorough), and the question parameter's 'broad/multi-part is fine' framing reinforces the decomposition design. This exceeds the baseline's minimum.

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 combination: 'Grounded multi-source research across Pipeworx's 1506 STRUCTURED data sources' decomposed into facets and routed to 5,767 tools in parallel. It explicitly disambiguates from siblings by stating 'this is NOT open-web search' and 'For a single lookup use ask_pipeworx instead.' An agent can clearly distinguish this from all 32 sibling tools.

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-not-to-use guidance: 'If you are not signed in, use ask_pipeworx instead — it works on every tier' and 'For a single lookup use ask_pipeworx instead.' It also states its sweet spot ('Best for broad/multi-part questions over structured data') with concrete example questions, leaving no inference burden on the agent.

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