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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the bar for added value is high. The description clears it: it discloses the live candidate-testing mechanism, the temporal fact that no candidate is active (dated 2026-07-26), the comparison-against-stable evaluation behavior, and that it 'falls back to nothing' yet is a fully working router. This dynamic-state context is exactly what annotations cannot encode.

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?

Well-organized: identity and parity first, then current state, then usage instruction, then the no-fallback reassurance. Concrete specifics (5,798 tools, the 2026-07-26 date) add credibility and precision. Some repetition of the 'identical/matches' point across the first, third, and fourth sentences is the only blemish; otherwise every clause earns its place.

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 with one required string parameter, rich safety annotations, and no output schema, this description covers what it is, its current live behavior, when to use it, and its functional guarantee. The response-shape gap is bridged by deferring to 'same response shape' as ask_pipeworx, which is adequate given the stable sibling is listed nearby. The residual gap is that an agent unfamiliar with ask_pipeworx still has no explicit statement of what the router actually returns.

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) are already documented in the schema itself with their alias relationships. The description adds no parameter-level meaning beyond 'same arguments' as ask_pipeworx, which is a functional equivalence claim rather than semantic enrichment. Baseline 3 per the rubric is appropriate when the schema carries the full weight.

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?

Identifies a specific resource — a 'universal router' over 5,798 tools — and clearly frames its identity as the beta of ask_pipeworx, distinguishing it from the stable and grounded siblings. The scope ('same arguments, same response shape') and current parity state are stated precisely. However, the core function (answering natural-language questions by routing across tools) is conveyed indirectly through the schema and the reference to ask_pipeworx rather than stated head-on.

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?

Explicitly instructs when to use it: 'Use it exactly like ask_pipeworx when you want the newest routing,' with the experimental-edge rationale and the note that results feed merge decisions against the stable router. It names the stable alternative and discloses the current matching state. It does not state an explicit exclusion (e.g., prefer stable when routing consistency matters), which keeps it just below a 5.

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