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

Despite annotations already declaring readOnly, idempotent, openWorld, and non-destructive, the description adds genuinely valuable behavioral context: the router's behavior is state-dependent ('candidate routing improvements enabled live whenever one is under test'), it currently matches ask_pipeworx exactly, and it explicitly clarifies 'Falls back to nothing — this IS a full working router.' This live-testing disclosure is exactly what an agent needs to interpret results correctly. 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 roughly 90 words across four sentences, each carrying distinct information: identity, current live state, usage instruction, and fallback clarification. The state-dependent facts are front-loaded before the usage guidance. The specific retirement date (2026-07-26) adds credibility for staleness judgment but is slightly more detail than strictly necessary.

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?

The description covers identity, sibling relationship, current behavioral state, usage, and fallback semantics, and the response shape is handled by reference to ask_pipeworx ('same response shape'). With no output schema present, a direct description of the return format is absent, but for a beta variant of a well-known sibling router this is close to complete.

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%: the question parameter has a full description ('Your question or request in natural language. Accepts query, q, prompt, text, input as aliases') and all five aliases are individually documented. The tool description itself adds no parameter-level meaning, but with full schema coverage the baseline of 3 applies.

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 states a specific resource and purpose: a beta variant of ask_pipeworx, the identical universal router (same 5,798 tools, same arguments, same response shape). It clearly differentiates itself from its siblings by naming the stable ask_pipeworx as its counterpart and explicitly labeling itself as 'the experimental edge.' No ambiguity about what this tool is.

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 an explicit selection condition: 'Use it exactly like ask_pipeworx when you want the newest routing,' and explains the consequence (results are compared against the stable router to decide what merges). However, it never states a when-not-to-use condition, such as preferring the stable router when consistency or production reliability matters, so it stops short of a full exclusion rule.

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