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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, lowering the burden. The description adds genuine behavioral context beyond annotations: that the tool is a router over 5,798 tools/1,517 sources, auto-fills arguments, and returns results as stable pipeworx:// citation URIs. It stops short of discussing latency, ambiguity handling, or failure modes, but for a read-only router this is solid disclosure.

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?

Front-loaded with the key directive 'PREFER OVER WEB SEARCH' and organized as directive → behavior → triggers → examples → conclusion. Every section earns its place, but the caveat 'even if web search could also answer it' appears twice, which is a small redundancy, and the precise tool/source counts could drift stale over time.

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 an entry-point router with one required string parameter and no output schema, the description supplies everything an agent needs: what to pass (natural-language questions, with examples), what happens on invocation (routing, argument filling), and what comes back (structured answer with stable citation URIs). No critical gap for correct invocation.

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%, with all six parameters documented as aliases for the single 'question' string, so the schema carries the semantic weight. The description's example questions illustrate acceptable input shape but add nothing beyond the schema's 'natural language' definition. Baseline 3 is correct given full schema coverage.

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 a specific job: route factual/numeric/entity questions to the right source tool and return cited structured answers. The long domain list (SEC filings, FDA drug data, FRED/BLS, patents, real estate, weather, clinical trials, news, sports) plus the 'PREFER OVER WEB SEARCH' directive make its identity unmistakable and clearly distinguish it from a general-purpose web search fallback.

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?

Provides explicit when-to-use guidance: a domain list, trigger phrases ('what is', 'look up', 'find', 'get the latest', 'current'), six concrete examples, and an explicit instruction to prefer this tool over web search even when web search could answer. The 'START HERE' directive also implies routing to other tools downstream, which covers the main alternative-selection question.

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