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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavior: identical arguments and response shape to ask_pipeworx, live experimentation semantics, an outcome-evidence retirement date (2026-07-26), and the explicit statement that it falls back to nothing because it is a full router in its own right. Latency, cost, or divergence risk between candidates is not discussed, keeping it short of a 5.

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?

Front-loaded with the identity and the delta from ask_pipeworx, then the current-state caveat, then the closing clarification about fallback. Density is high but the parenthetical "(same 7,293 tools, same arguments, same response shape)" is doing real work. The final clause "just the experimental edge" is slightly rhetorical but reinforces the no-fallback point.

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-blast-radius router with nine params and no output schema, the description covers purpose, sibling relationship, current operational state, and failure semantics. An agent has enough to choose correctly between this and ask_pipeworx. What it does not cover is the response envelope beyond "same response shape" and any mention of _meta fields, though the input schema already describes _meta.pack_scope.

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 schema itself documents the question field, all seven aliases, and the pack-scoping fallback in detail. The description only asserts "same arguments," which is a correct pointer rather than new semantics, so the schema carries the load as intended. Baseline would be 3, but the schema's own high-quality parameter documentation plus the accurate equivalence claim makes this complete; scored 5 on the evidence that nothing is left ambiguous.

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+resource frame ("universal router" that answers a question by routing to 7,293 tools) and immediately differentiates itself from ask_pipeworx by naming it and defining the delta: candidate routing improvements enabled when one is under test. An agent can tell this apart from the stable router and from ask_pipeworx_grounded without opening any 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?

"Use it exactly like ask_pipeworx when you want the newest routing" gives explicit when-to-use plus the selection criterion versus the sibling. It also effectively signals when NOT to bother, by disclosing that no candidate is active right now and results currently match ask_pipeworx exactly. What's missing is an explicit directive such as "prefer ask_pipeworx for production-stable answers," leaving the final call to inference.

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