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

The description goes far beyond the annotations (readOnlyHint, openWorldHint, idempotentHint) by disclosing account requirements, depth-specific behavior (gap recovery, contradiction scan), parallel decomposition into facets, the structure of the findings packet (verbatim evidence, confidence, source, fetched_at, citations), the explicit gaps[] handling (never invents), second-hop iteration, semantic excerpting, and expected latency (15-90s). It even clarifies citation_uri resolvability. This is comprehensive behavioral disclosure that fully complements, and never contradicts, the 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?

The description is quite long, but every sentence carries essential information: account requirements, usage alternatives, internal mechanics, citation behavior, time estimates. It is front-loaded with the most critical info (account requirement, fallback to ask_pipeworx) and then layers details. Slightly verbose and stream-of-consciousness, but not padded. It could benefit from clearer paragraph breaks, but remains efficient relative to its coverage.

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 the tool's complexity (2 params, no output schema), the description covers all critical aspects: prerequisites (account, paid tier), alternatives, scope, behavioral details, latency, gap handling, and citation specifics. An agent can effectively decide whether to use this tool and how to set parameters without needing additional context. The absence of an output schema is compensated by the detailed description of the findings packet.

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?

Although the input schema already provides full 100% coverage for both parameters (question and depth), the description adds meaningful context beyond the schema: it explains that depth:'thorough' requires a paid plan, gives time expectations per depth, and clarifies the decomposition behavior tied to depth. It also describes how the 'question' parameter should be phrased (natural language, broad/multi-part is fine). This enriches the schema without redundancy.

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 states the tool's purpose: grounded, multi-source research across structured data sources (SEC, FRED, FDA, etc.) in one call. It explicitly distinguishes itself from open-web search and names the alternative ask_pipeworx for single lookups, making it easy for an agent to select this tool for broad, multi-part structured-data questions. The verb 'research' and resource '1496 structured data sources' are specific and 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?

The description provides explicit when-to-use and when-not-to-use guidance: it names ask_pipeworx as the alternative for single lookups and for breaking/colloquial current-news topics, explaining that deep_research returns empty gaps[] for such topics. It also explains the benefit for multi-step questions via depth levels. This is optimal routing guidance, leaving no ambiguity for the agent.

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