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

Even though annotations already mark the tool as read-only, open-world, and idempotent, the description adds substantial behavioral context: it returns a findings packet with verbatim evidence, confidence, source, fetched_at, and a stable pipeworx:// citation; it includes explicit gaps[] and never invents data; it returns contradictions[] for standard and thorough depths; it semantically excerpts large records; and it provides latency expectations. It also discloses the auth requirement and paywall, which annotations do not capture. No contradiction with annotations exists.

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 dense and front-loaded with critical facts: the account requirement, fallback tool, and core capability come first. However, it is somewhat repetitive—'use ask_pipeworx' appears multiple times and depth behavior is restated from the schema—making it longer than necessary. It earns a 4 because nearly every retained detail adds value, but it could be tightened without losing information.

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 values, and it does so thoroughly: findings packet contents, gap handling, contradictions[], hop field, citation_uri fetchability, semantic excerpting, and latency. It also covers auth prerequisites, exclusions, alternatives, and best-fit use cases. For a complex research tool with two parameters and no output schema, this is complete enough for an agent to invoke it 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%, so the baseline is 3; the schema already thoroughly documents both 'question' and 'depth' including enum values and their behavioral differences. The description adds some context, such as the paid requirement for thorough and expected latency, but largely restates what the schema already says about depth semantics. It does not meaningfully enhance understanding of parameter values beyond the schema, so it stays at baseline.

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 states a specific verb and resource: 'Grounded multi-source research across Pipeworx's 1506 STRUCTURED data sources... in ONE call.' It is clearly distinguished from siblings by explicitly saying it is not open-web search and by positioning itself against ask_pipeworx, which prevents an agent from confusing it with the other lookup-style tools in the sibling list.

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/when-not guidance with named alternatives: 'If you are not signed in, use ask_pipeworx instead,' 'For a single lookup use ask_pipeworx,' and 'NOT for BREAKING/colloquial current-news: use ask_pipeworx (or ask_pipeworx_beta).' It also states exactly what it is best for: broad/multi-part questions over structured data. An agent can confidently select between deep_research and its siblings based on this description alone.

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