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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds genuinely non-obvious behavioral context on top: this is an experimental edge whose routing may change live when a candidate is under test, that no candidate is currently active (so behavior currently matches ask_pipeworx exactly), and crucially that it 'falls back to nothing' — it is a full working router, not a fragile wrapper. That last clarification prevents a likely misjudgment. Not a 5 because it doesn't discuss how a candidate test might alter response quality or whether results are flagged as experimental.

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 earning its place: purpose/identity, current state with a specific retirement date, usage directive, and a misconception-preventing clarification. The critical scoping info ('identical universal router', 'currently matches ask_pipeworx exactly') is front-loaded. It is slightly wordy in the middle ('the last was retired on outcome evidence 2026-07-26' is more detail than strictly needed), 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 beta twin of a stable tool, the description covers the unusual aspects well: experimental status, current parity with the stable router, usage conditions, and the reassurance that it is fully functional. Since there is no output schema, the description's pointer to 'same response shape' as ask_pipeworx is a reasonable delegation to the sibling rather than a gap. It is not a 5 because it assumes the agent will consult ask_pipeworx for response format details, and it never says what kinds of questions are appropriate for a universal router.

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% — all six parameters (question plus five aliases: q, text, input, query, prompt) are already fully documented in the schema, so the baseline is 3. The description adds no parameter-level meaning beyond noting 'same arguments' as ask_pipeworx, which confirms parity but doesn't enrich understanding of any individual parameter. It meets the baseline but doesn't exceed it.

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 identifies the tool as a beta twin of ask_pipeworx: an identical universal router with experimental routing improvements, and explicitly scopes it ('same 5,798 tools, same arguments, same response shape'). It distinguishes itself from the stable sibling ask_pipeworx by the beta/experimental framing. It stops short of 5 because the actual user-facing function ('answer my question by routing to the tool network') is only conveyed indirectly via 'universal router' and 'use it exactly like ask_pipeworx' — an agent unfamiliar with ask_pipeworx would need to open that sibling to fully understand the operation.

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 when-to-use directive: 'Use it exactly like ask_pipeworx when you want the newest routing,' and explains the evaluation context ('results are compared against the stable router to decide what merges'). It names the primary alternative (ask_pipeworx) and the condition that selects this variant. It doesn't provide exclusion criteria, such as when to prefer the stable router or ask_pipeworx_grounded, so it misses the 'when-not-to-use' part of a 5.

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