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

Beyond the annotations (readOnly, idempotent, openWorld), it discloses live experimental behavior, the current inactive-candidate state, and the critical no-fallback guarantee ('this IS a full working router'). This is exactly the kind of behavioral context annotations cannot express.

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?

The description is front-loaded with the core identity and difference, then gives status and usage. A few phrases are redundant ('Falls back to nothing — this IS a full working router'), but no sentence is wasted and length is reasonable for a beta-status tool.

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?

It covers the essential runtime context: experimental status, current equivalence to stable, exact equivalence of tool set/arguments/response shape, and no fallback. Without an output schema, the response-shape reference relies on the sibling's definition, leaving a small gap, but the tool is callable with the provided information.

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 are documented as aliases for the single required 'question'. The description merely says 'same arguments' and adds nothing about formats or usage, which is acceptable because the schema carries the full burden.

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 a concrete object ('beta version of ask_pipeworx', 'identical universal router') and explains the experimental differentiator: candidate routing improvements tested live. This clearly separates it from stable ask_pipeworx and ask_pipeworx_grounded. The only minor opacity is 'universal router' jargon, but the sibling reference resolves it.

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 says to use it 'exactly like ask_pipeworx when you want the newest routing' and explains results are compared with the stable router. It gives a positive selection condition, but does not say 'use stable ask_pipeworx when you want proven behavior', so exclusions are only implicit via 'beta' and 'experimental edge'.

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