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

The description adds substantial behavioral context beyond the annotations: account requirements and paid depth, decomposition and parallel routing, the findings packet structure (verbatim evidence, confidence, source, fetched_at, pipeworx:// citation), explicit gaps[] for unanswered facets, the 'never invented' guarantee, hop/citation_uri semantics, contradictions[], semantic excerpting, and expected latency. Annotations are readOnly/openWorld/idempotent and the description's behaviors are consistent with those hints.

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 long but every section earns its place: account constraints and alternatives are front-loaded, then the core capability, then depth behaviors, citation semantics, and latency. It is a wall of text rather than structured bullets, which slightly hurts scannability, but it is dense and non-redundant for a tool with this much behavioral nuance.

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?

Given there is no output schema, the description carries the burden of explaining return semantics, and it succeeds: it defines the findings packet fields, gaps[], contradictions[], citation_uri conditions, and latency expectations. It also covers edge cases such as unanswered facets, deep passages in long records, and auth tiers. An agent has everything needed to invoke the tool correctly and interpret the result.

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 baseline is 3; the schema already fully describes 'question' and the depth enum including per-depth behavior. The description adds the payment constraint for depth:'thorough' and restates examples, but it does not materially extend the semantic meaning of the parameters beyond what the schema provides.

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: it performs grounded multi-source research over 1517 structured data sources in one call, explicitly distinguishing itself from open-web search. It also differentiates from ask_pipeworx by stating that deep_research decomposes questions and routes facets in parallel to specialized tools, while a single lookup should use ask_pipeworx. This is more than sufficient for an agent to select the tool correctly.

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 routing guidance: if not signed in, use ask_pipeworx instead; if the request is a single lookup, use ask_pipeworx; deep_research is best for broad/multi-part questions over structured data. It also warns that deep research is NOT open-web search, preventing a common misuse. This fully addresses when and when-not to use the tool relative to siblings.

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