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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context beyond annotations: candidate routing improvements are 'enabled live whenever one is under test,' meaning behavior can change between calls, and the current stable state is pinpointed ('no candidate is active right now... retired on outcome evidence 2026-07-26'). It also clarifies the tool is fully functional rather than a degraded fallback. No contradiction with annotations — a read-only, non-destructive router is consistent with the hints.

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 carrying decision-relevant content: identity/relationship to ask_pipeworx, current candidate state, usage directive, and functional-status clarification. The most important facts (beta twin, identical behavior) are front-loaded. Slightly verbose with the specific retirement date '2026-07-26,' but that precision is useful for timing judgments, so no sentence is wasted.

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-meaningful-parameter router with annotations covering safety, the description is nearly complete: it explains what the tool is, its current behavior, when to use it, and that it is fully functional. The one gap is that the response shape is deferred to 'same response shape' without describing what that shape is — and there is no output schema to fill the gap. Since the sibling ask_pipeworx exists in the same tool set and the description points the agent there, this is an acceptable but real omission.

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%: the required `question` parameter is documented as 'Your question or request in natural language' and all five aliases (q, text, input, query, prompt) are individually described. The description's phrase 'same arguments' merely reinforces the schema rather than adding new semantic meaning. With full schema coverage, the baseline of 3 applies; no parameter-level compensation is needed.

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 clearly identifies the tool as 'Beta version of ask_pipeworx: identical universal router (same 5,743 tools, same arguments, same response shape)' — specifying the resource (universal router over 5,743 tools) and scope (identical to ask_pipeworx) while naming the sibling it relates to. It distinguishes itself from the stable sibling via 'candidate routing improvements' and 'experimental edge.' However, the core action of the router (that a natural-language question gets routed to a tool or answer) is only implied, not explicitly stated, so an agent unfamiliar with ask_pipeworx would infer rather than read the tool's function.

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?

Provides explicit when-to-use guidance: 'Use it exactly like ask_pipeworx when you want the newest routing.' It names the alternative (the stable router/ask_pipeworx) and states the comparison purpose: 'results are compared against the stable router to decide what merges.' The clarification 'Falls back to nothing — this IS a full working router' prevents the agent from treating it as a stub or fallback, which is a decision-relevant exclusion.

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