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

Goes far beyond the readOnly/idempotent annotations: it discloses the grounded data universe, parallel facet routing, gaps[] for unanswerable facets, 'never invented', contradiction[] behavior, semantic excerpting, and latency expectations. No statement conflicts 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?

Long, but organized and front-loaded: account gate first, core capability second, then examples, alternatives, and detailed return/latency behavior. Minor redundancy with the depth schema, but every sentence contributes actionable context; not quite the two-sentence ideal.

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 compensates by specifying the findings packet (verbatim evidence, confidence, source, fetched_at, citation), gaps[], contradictions[], citation_uri behavior, and latency. It covers prerequisites, alternatives, expected outputs, and limitations, so an agent can decide and invoke 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 description coverage is 100%, so the schema already carries the parameter load for `question` and `depth`. The description adds useful examples of multi-part questions and ties paid gating/iteration to depth, but this is mostly reinforcement rather than new parameter meaning; baseline 3 is appropriate.

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 exactly what it does: 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources' in ONE call, with decomposition and parallel routing. It also differentiates itself from siblings by saying 'this is NOT open-web search' and naming ask_pipeworx as the single-lookup alternative. Clear verb+resource+scope.

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 conditions use: signed-in required, use ask_pipeworx if not signed in, best for broad/multi-part structured-data questions, and 'For a single lookup use ask_pipeworx instead.' This gives the agent both positive and negative selection criteria.

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