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

Annotations already mark this read-only, open-world, and idempotent; the description layers substantial behavioral context on top: the account/paywall prerequisite, latency (15–60s, up to ~90s for thorough), and the exact findings-packet shape (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation, with explicit gaps[] for unanswered facets). The 'never invented' clause and contradictions[] disclosure manage agent expectations about hallucination and disagreement, and depth-tier procedural differences (gap-recovery hop, iterative lead-chasing) are spelled out.

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 a dense ~300-word block for a 2-parameter tool. The ask_pipeworx fallback guidance effectively appears twice ('If you are not signed in, use ask_pipeworx instead — it works on every tier' and 'For a single lookup use ask_pipeworx — it works on every tier'), and depth-tier mechanics are re-explained in prose even though the schema already documents the enum. Information is mostly front-loaded (account and fallback first) and nearly every clause carries unique operational content, but the length and redundancy keep it from being tight.

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-param tool with no output schema, the description carries the full burden of explaining the return contract — and it does: findings packet with verbatim evidence, confidence, source, fetched_at, stable citation, explicit gaps[], and contradictions[]. It also covers the auth prerequisite, the unpaid fallback, latency expectations, and citation resolvability ('a citation you get back is always fetchable'). An agent has everything needed to invoke it correctly and set user expectations.

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 the schema already documents both question and depth fully (baseline 3). The description adds value beyond it: two example questions showing what a good 'question' looks like, and the operational constraint that depth='thorough' requires a paid plan — which the schema does not state. It does not add much about question format beyond the schema's 'natural language, broad/multi-part is fine,' so the extra credit is moderate.

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 and resource — 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources' — plus the mechanism: decompose the question into facets, route to 5,798 tools in parallel, return a findings packet. It explicitly distinguishes itself from siblings: 'this is NOT open-web search' and 'For a single lookup use ask_pipeworx.' An agent can tell exactly what this tool is for without opening the 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?

Gives explicit when-to-use criteria: 'Best for broad/multi-part questions over structured data' with two concrete example phrasings. Gives when-not-to-use: 'For a single lookup use ask_pipeworx.' Also names the alternative for unsigned-in users: 'If you are not signed in, use ask_pipeworx instead — it works on every tier.' Nothing is left to inference.

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