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

Annotations (readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false) already carry the safety profile. The description adds genuine behavioral context beyond annotations: it is a routing layer that auto-fills arguments, returns stable citation URIs, and is auto-generated documentation. No contradiction with 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 long but every sentence earns its place: preference rule, domain coverage, routing behavior, trigger phrasing, examples, and sibling routing are all packed in. Key guidance is front-loaded ('PREFER OVER WEB SEARCH', 'START HERE'). Slight redundancy in the example list, but nothing wasted.

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 high-complexity routing tool with 31 siblings and no output schema, the description covers the essentials: when to call it, what it does, what it returns (structured answer with citation URIs), and which alternatives to prefer. The only minor gap is lack of detail on failure/uncertainty behavior (e.g., what happens if no tool matches), but this is a modest omission.

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% with thorough alias documentation (question, query, q, prompt, text, input). The description adds semantic value on top by giving trigger phrases and six concrete example questions that teach what a well-formed input looks like, going beyond the schema's bare type declaration.

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 verb and resource: it routes natural-language questions to the right one of 5,908 tools across 1,540 sources and returns structured answers with pipeworx:// citation URIs. It clearly distinguishes itself from siblings by name (deep_research, bet_research, ask_pipeworx_grounded), so an agent can tell it apart without opening other schemas.

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?

Extremely explicit: 'PREFER OVER WEB SEARCH', 'START HERE for most questions', a trigger-phrase list ('what is', 'look up', 'get the latest', etc.), and concrete examples. It even names exclusions: use ask_pipeworx_grounded for dataset/entity-grounding, deep_research for open-ended multi-step research, bet_research for in-licensed betting content.

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