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

Annotations already cover read-only/idempotent/non-destructive behavior, so the bar is lower. The description adds substantial value: explains latency (15-60s, up to ~90s for thorough), gap handling (explicit gaps[] never invented), contradiction scanning, semantic excerpting of large records, citation behavior (stable pipeworx:// references, always fetchable), and account/depth requirements.

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 information-dense but somewhat sprawling for an initial tone (ACCOUNT REQUIRED, depth tier pricing, internal implementation details like the 5,798 tools). The sentences run long and mix operational details (latency, follow-up passes) with usage guidance. It earns its place mostly, but a clearer top-line 'what + when' structure would improve it.

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?

Despite no output schema, the description thoroughly explains the return shape (findings packet, verbatim evidence + confidence + source + fetched_at, citations, gaps[], contradictions[]) and the failure modes (gaps never invented, latency expectations, account tier gate). An agent has everything it needs to decide when to call this and what to expect back.

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 both parameters are documented. The description adds context by explaining what 'depth' values actually do (quick=3 facets single-hop, standard=3 with gap recovery, thorough=6 paid with iterative hop) and clarifies that the question parameter accepts natural language, multi-part questions. Justification referencing the enums' behavioral implications goes beyond schema.

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 clearly identifies deep_research as a grounded multi-source research tool across Pipeworx's 1517 structured data sources, explicitly distinguishing it from open-web search and naming its sibling ask_pipeworx as the alternative. It specifies what it does — decomposes questions, routes facets in parallel, returns a findings packet — and provides example use cases.

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 states when to use this tool (broad/multi-part questions over structured data) and when not to (single lookup → use ask_pipeworx instead). Also gives clear account requirements, noting that unsigned users should use ask_pipeworx. It even differentiates between depths (quick/standard/thorough) and what each provides.

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