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

Annotations already carry the safety profile (readOnly, openWorld, idempotent, non-destructive), so the description earns credit for adding substantial behavioral context: latency (15-60s, up to ~90s thorough), signup/pricing requirements, the never-invents-data guarantee via explicit gaps[], contradictions[] on standard/thorough, semantically-excerpted records (not head-truncated), and citation_uris present only when actually resolvable. No contradiction with 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?

A dense ~250-word paragraph that front-loads the auth gate before the core purpose and flows logically through behavior, return format, and latency. Nearly every sentence earns its place given the tool's complexity and lack of an output schema. Deductions for the wall-of-text single-paragraph structure and slight redundancy with the schema's enum descriptions of depth.

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 return-format disclosure unaided and delivers it thoroughly: findings packet contents (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation), gaps[], contradictions[], hop field, and when a citation is guaranteed fetchable. Auth, pricing, latency, alternatives, data-scope caveats, and anti-hallucination behavior are all covered — nothing an agent needs to invoke 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?

Scheam coverage is 100%, so baseline is 3. The description adds real value by showing how to phrase questions ('compare X and Y's regulatory + financial exposure') and by clarifying the behavioral consequence of each depth tier (hop count, gap-recovery, contradictions[] scan, latency). Some hop mechanics are repeated from the schema's enum descriptions, so the increment is modest but genuine.

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... in ONE call.' It explicitly disambiguates from siblings by declaring 'this is NOT open-web search' and by contrasting itself with ask_pipeworx for single lookups, so an agent can distinguish it without opening sibling 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?

Gives explicit when-to-use and when-not-to-use guidance: 'Best for broad/multi-part questions over structured data' with concrete examples, and 'For a single lookup use ask_ipeworx instead.' It also gates on auth, telling unsigned-in agents to fall back to ask_ipeworx 'it works on every tier,' and explains when 'thorough' depth is worth the paid plan.

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