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

The annotations already carry the safety profile (readOnlyHint, openWorldHint, idempotentHint, destructiveHint false), and the description adds genuinely new behavioral context beyond them: the live-testing regime where candidates are enabled and retired, the dated state claim ('the last was retired on outcome evidence 2026-07-26'), and the direct parity statement 'currently matches ask_pipewrox exactly.' The line 'Falls back to nothing — this IS a full working router' preempts a common misconception about beta tools. No contradiction with the 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, each with a distinct job: identity and scope, current state with a dated evidence trail, usage condition, and a misconception-killing guarantee. Specific details like the 5,798-tool count and the 2026-07-26 date add credibility without bloating. The final sentence is slightly redundant with the first ('this IS a full working router' versus already defining it as a full router), which keeps it from a 5.

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 tool whose identity is defined relative to a sibling, the description covers the essentials: current parity with ask_pipewrox, the condition under which to prefer it, response-shape parity via 'same response shape,' and the annotations complete the safety profile. With no output schema present, a brief note on what the response actually contains beyond 'same response shape' would round it out, but the description is sufficient for an agent to invoke it correctly.

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 already documents `question` and all five aliases, even stating that query, q, prompt, text, and input are accepted as aliases. The description adds only the cross-tool note 'same arguments,' which conveys no new parameter semantics. Baseline 3 applies because the schema carries the full load.

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 — a universal router over 5,798 tools that answers questions — and explicitly differentiates itself from its siblings: it is the 'Beta version of ask_pipewrox' carrying 'candidate routing improvements' and 'the experimental edge' relative to the 'stable router.' The parity claim 'currently matches ask_pipewrox exactly' makes the distinction concrete rather than abstract.

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?

Gives an explicit trigger condition: 'Use it exactly like ask_pipewrox when you want the newest routing,' and names the alternative (the stable ask_pipewrox) plus the evaluation context ('results are compared against the stable router to decide what merges'). No crisp when-not statement is written out — the agent must infer that the stable router is the choice when experimental routing is not wanted — so the exclusion is implied rather than explicit.

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