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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, non-destructive), so the bar is lower, but the description adds genuinely useful behavior beyond them: the current live status ('No candidate is active right now... matches ask_pipeworx exactly'), the dated retirement evidence, and the clarification that this 'falls back to nothing — this IS a full working router.' These prevent the agent from treating it as a stub or assuming experimental behavior is currently active. 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?

Four sentences with a logical flow: identity and scope first, then live experimental status, then usage instruction, then a functionality caveat. The critical facts (current parity, how to use) are front-loaded. Minor redundancy exists in 'identical... (same 5,804 tools, same arguments, same response shape),' where the enumeration restates 'identical,' and the dense phrasing 'candidate routing improvements enabled live whenever one is under test' could be smoother. No wasted sentences overall.

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 (a router with one required natural-language param), the description covers the essentials well: what it does, how it differs from the stable sibling, its current status, usage, and confirmation of full functionality. It compensates for the missing output schema by explicitly delegating to ask_pipeworx ('same response shape'). The only real gap is the unspecified behavior delta when a candidate is live, which is arguably unknowable by definition during a routing experiment.

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% — all six parameters (question plus five aliases) are fully documented, so the schema carries the heavy lifting and the baseline is 3. The description adds only the parity note ('same arguments' as ask_pipeworx), which is useful context for an agent that already knows the stable tool, but it doesn't enrich the meaning of the parameters themselves. The baseline 3 stands.

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 role: a universal router with the same 5,804-tool surface as ask_pipeworx, explicitly differentiated as the beta/experimental edge. It names the key sibling (ask_pipeworx) and clarifies the relationship (identical now, candidate routing when under test), so an agent can distinguish it without opening either schema. The identity is concrete, not a tautology of the title.

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 usage directive: 'Use it exactly like ask_pipeworx when you want the newest routing,' and explains why (results are compared against the stable router to decide merges). It names the alternative router directly. It stops short of stating an explicit exclusion ('use ask_pipeworx when you need stable-only behavior'), though the 'experimental edge' framing implies it, so it doesn't quite earn a 5.

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