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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description adds real context beyond them: candidate routing is A/B compared against the stable router to decide merges, and 'Falls back to nothing — this IS a full working router.' That preempts the wrong inference that a beta endpoint is a stub or partial service. It does not describe failure modes, latency, or how _meta comparison fields surface, so it stops at 4.

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 core fact (beta variant, identical to ask_pipeworx, no candidate currently active) is front-loaded in the first sentence. The closing 'Falls back to nothing — this IS a full working router, just the experimental edge' is slightly defensive padding, but it earns its place by killing a likely misread.

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 single-question router entry point with 9 params at full schema coverage and no output schema, the description supplies the two things an agent actually needs: what this is relative to ask_pipeworx, and that it returns the same shape. It could say more about when routing results are logged or compared, but nothing essential for a correct call is missing.

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% and the pack-scoping semantics, including the ignored-slug and full-catalog fallback behavior, are fully documented in the schema itself. The description only says 'same arguments', adding nothing beyond the structured fields. Baseline 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?

States a specific resource (a beta/experimental variant of the universal router) and explicitly frames it against its sibling: 'identical universal router (same 7,130 tools, same arguments, same response shape)' vs. ask_pipeworx. An agent can tell exactly what this is and that it is a variant of a named sibling without opening a schema.

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?

Names the alternative and the selecting condition: 'Use it exactly like ask_pipeworx when you want the newest routing.' It also states the current state ('No candidate is active right now... so this currently matches ask_pipeworx exactly'), which implicitly tells the agent there is no behavioral difference today. It stops short of an explicit 'prefer ask_pipeworx unless X' recommendation, leaving the tie-break to inference.

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