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

Annotations carry the safety profile (readOnlyHint, idempotentHint, openWorldHint, non-destructive), and the description adds substantial behavior beyond that: the account/paywall requirement, the parallel facet decomposition across 5,798 tools, the findings packet shape (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation), the gaps[] honesty guarantee ('never invented'), contradictions[] for standard/thorough, semantic excerpting rather than head-truncation, and timing expectations (15-60s, ~90s worst case). The citation_uri fetchability caveat is especially valuable operational context.

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 but every sentence carries operational value — account gating, sibling routing, mechanism, return format, honesty guarantees, timing. It is front-loaded with the most important gating fact (account required). The main flaw is structural: the depth-level mechanics are packed into a long parenthetical-heavy sentence that is harder to parse than the rest, and some specifics (1,517 sources, 5,798 tools) are more promotional than decision-relevant. Not waste, but not optimally organized.

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 complex tool with no output schema, the description covers the complete operational picture: prerequisites, alternatives, what it does internally, what the return packet contains, how missing data is handled, latency expectations, depth options with costs, and the fetchability guarantee for citations. There is no output schema, so the described findings-packet structure is essential — and it is provided. Nothing an agent needs to call 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?

Schema coverage is 100%, so the baseline is 3. The schema already documents the depth enum with facet counts and hop behavior. The description adds meaning beyond this: it ties 'thorough' to the paid plan ('needs a paid plan'), explains the gap-recovery hop ('re-angles unanswered facets'), and describes thorough's lead-chasing ('chases the best leads from the first pass'), which clarifies the practical cost/benefit tradeoff of each depth value.

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 and resource: grounded multi-source research across 'Pipeworx's 1517 STRUCTURED data sources' in one call, and explicitly disambiguates from open-web search ('this is NOT open-web search'). It also scopes the use case to 'broad/multi-part questions over structured data', which distinguishes it from the sibling single-lookup tool ask_pipeworx and the narrower bet_research/validate_claim 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 an explicit alternative and condition: 'If you are not signed in, use ask_pipeworx instead — it works on every tier.' It also draws the boundary against single lookups: 'For a single lookup use ask_pipeworx instead,' and gives positive examples of when deep_research is the right choice ('compare X and Y's regulatory + financial exposure'). An agent can make a correct routing decision with no inference.

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