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

Beyond annotations that mark this as read-only and idempotent, the description discloses router behavior: it auto-fills arguments, selects among thousands of tools, and returns structured answers with stable pipeworx:// citation URIs. This helps an agent set expectations about output and provenance. It does not mention rate limits or failure modes, but the annotations already cover the safety profile.

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 front-loaded with the most important guidance and uses readable lists and examples. However, the final sentence about deep research is grammatically awkward and convoluted ('deep research uses live news + the *-news-feeds packs'), and some advice is repeated across 'PREFER OVER WEB SEARCH', 'Use whenever', and 'START HERE'. It could be tightened without losing information.

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 a meta-router with no output schema, the description covers the key decision points: what domains it covers, how to trigger it, what it returns, and when another tool may be better suited. It lacks explicit caveats about unsupported question types, but the 'START HERE for most questions' framing plus examples is sufficient for an agent to invoke it 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 coverage is 100% and the main parameter 'question' is documented as natural language with aliases. The description adds valuable examples of valid queries and enumerates acceptable question types, giving semantic meaning beyond the schema's generic 'Alias for question' text. This is more than the baseline 3 because it illustrates concrete inputs.

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?

Description clearly identifies ask_pipeworx as a factual question router: it states 'Routes the question to the right one of 5,743 tools', enumerates specific domains (SEC filings, FDA, FRED/BLS, patents, etc.), and provides concrete example queries. This resource and scope make it distinct from sibling tools like deep_research or search_within, and the use of 'PREFER OVER WEB SEARCH' signals its unique position.

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 triggers: prefer over web search for current/historical data, use for 'what is', 'look up', 'find', 'get the latest', and 'START HERE for most questions'. It names deep_research as the alternative for broad multi-part questions, though the phrasing is indirect ('deep research uses live news + ...') and no distinction is made for ask_pipeworx_beta/grounded. Still, an agent gets clear when-to-use guidance.

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