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

Annotations already cover readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the bar for added value is high. The description goes well beyond annotations: it discloses that candidate routing improvements may be enabled live under test, that no candidate is active right now (retired on outcome evidence 2026-07-26), that it currently matches ask_pipeworx exactly, and that it is a fully working router rather than a stub. This time-varying behavior is exactly the kind of trait an agent needs disclosed.

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 dense sentences, each earning its place: identity, current experimental state, usage guidance, and disambiguation from a stub. The information is front-loaded with the beta/identical-router statement. Slight redundancy between 'same 5,743 tools, same arguments, same response shape' and 'currently matches ask_pipeworx exactly' prevents a perfect 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 complex universal router with no output schema, the description is complete: it explains what the tool is, its live experimental routing behavior, current parity with the stable sibling, exactly when to use it, and explicitly rules out the 'falls back to nothing' misinterpretation. Response shape is covered by reference to the sibling ('same response shape'). Nothing an agent needs to invoke it correctly is missing.

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 schema already documents question and all five aliases (q, text, input, query, prompt) with descriptions. The description adds only 'same arguments' as a reference to ask_pipeworx, contributing no new meaning about format, constraints, or usage of the parameters. Baseline 3 is appropriate since 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 — 'beta version of ask_pipeworx', 'identical universal router' — and precisely delineates the relationship with its stable sibling (same 5,743 tools, same arguments, same response shape). An agent can distinguish it from ask_pipeworx and the 36 other siblings without opening the schema. It even clarifies it 'IS a full working router,' removing any ambiguity about what the tool does.

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 states the selection rule: 'Use it exactly like ask_pipeworx when you want the newest routing.' It names the stable comparator (ask_pipeworx), explains the evaluation workflow (results compared against the stable router to decide what merges), and warns that it 'falls back to nothing,' so the agent knows it is not a fallback-only probe.

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