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

Even with readOnlyHint/openWorldHint/destructiveHint annotations already present, the description goes far beyond them: it discloses one-call parallel decomposition, the findings packet structure (verbatim evidence, confidence, source, fetched_at, citation, gaps[], contradictions[]), the never-invented guarantee, fetchable citation_uri semantics, semantic excerpting for large records, and latency expectations. This gives the agent a rich behavioral model without contradicting any annotation.

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 almost every sentence is operationally relevant: account requirements and the alternative tool are front-loaded first, followed by core behavior, then return-format details, then depth-tier semantics and latency. It is dense rather than padded, though the length is at the upper edge and could be tightened slightly without losing meaning.

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 fully compensates by specifying the return packet, gap handling, contradiction reporting, citation semantics, and timing expectations. It also covers auth prerequisites, tier differences, and when to use sibling tools. For a two-parameter tool, nothing needed for correct invocation or interpretation of results 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?

The input schema already has 100% description coverage for both parameters, so the baseline is 3. The description adds genuine value beyond the schema by clarifying that 'thorough' requires a paid plan, that 'standard' and 'thorough' include a contradictions[] scan, and that facet decomposition is the core mechanism for the 'question' parameter. This is supplementary rather than repetitive.

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 opens with a specific action and resource: 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources' in one call, and explicitly distinguishes itself with 'this is NOT open-web search.' It also delineates its niche from ask_pipeworx for single lookups versus broad/multi-part research questions, making sibling differentiation unambiguous.

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?

Usage guidance is explicit and actionable: 'Best for broad/multi-part questions over structured data' is paired with direct exclusions like 'For a single lookup use ask_pipeworx', 'prefer ask_pipeworx' for breaking/current news, and 'If you are not signed in, use ask_pipeworx instead.' Depth tiers are also mapped to concrete behaviors, so an agent knows exactly when to select this tool and when to route elsewhere.

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