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

Annotations already cover safety (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description carries a lighter burden yet still adds rich behavioral context: the current state ('No candidate is active right now... currently matches ask_pipeworx exactly'), the live-swapping behavior when a candidate is under test, and the critical assurance 'Falls back to nothing — this IS a full working router, just the experimental edge.' This refutes the likely assumption that a beta tool might be a stubbed proxy.

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, live status, usage directive, and the working-router reassurance. The core identity is front-loaded ('Beta version of ask_pipeworx'). The only minor redundancy is that 'identical universal router' and 'Falls back to nothing — this IS a full working router' restate a similar point from different angles, but the latter addresses a real agent misconception so it earns its keep.

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 tool routing to 5,724 tools with no output schema, the description resolves the key uncertainties an agent would have: Is this a stub? (No — full working router.) Is it currently different from stable? (No — no active candidate.) What happens with results? (Compared to decide merges.) What safety profile? (Covered by annotations.) The response shape reference to ask_pipeworx plus the alias-heavy schema leaves no critical gap.

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 documents question and all five aliases (q, text, input, query, prompt) with descriptions. The description adds nothing parameter-specific beyond noting 'same arguments' as ask_pipeworx, so the baseline of 3 applies: the schema does the heavy lifting and the description doesn't need to compensate.

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 names the exact relationship to its stable sibling ('Beta version of ask_pipeworx: identical universal router') and quantifies scope ('same 5,724 tools, same arguments, same response shape'). It clearly distinguishes this from ask_pipeworx and ask_pipeworx_grounded by framing it as the experimental edge used to test routing improvements.

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 usage directive: 'Use it exactly like ask_pipeworx when you want the newest routing.' It also explains the purpose (results compared against stable router to decide merges), which tells the agent why choosing this variant matters. However, the when-not-to-use case (prefer the stable ask_pipeworx when you don't want experimental behavior) is only implied, not stated as an exclusion.

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