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

Annotations already cover readOnlyHint=true, idempotentHint=true, and destructveHint=false, so the safety profile is established. The description adds genuinely useful stateful context beyond that: candidate improvements are enabled live only when under test, no candidate is currently active as of the dated retirement, it currently matches ask_pipeworx exactly, and there is no fallback ('Falls back to nothing — this IS a full working router'). This lets the agent predict behavior accurately.

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 prose portion is tight and front-loaded: four dense sentences all carrying weight, with the beta identity established in the first phrase. However, the description payload also contains embedded, duplicated copies of the input/output schema and annotations as XML-tagged text, which bloats the field and repeats structured data that is already available separately.

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 one-required-param tool with no output schema, the description covers identity, current operational state, usage instructions, and the experimental/candidate-evaluation context — everything needed to call it correctly. The only gap is that it never describes what happens when a candidate IS active (e.g., whether outputs may deviate mid-test), though 'enabled live' implies variability.

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 dedscription coverage is 100% — each parameter (question plus aliases q, text, input) has a description in the schema. The description adds only the relational pointer 'same arguments ... as ask_pipeworx', which helps an agent already familiar with the sibling but adds no per-parameter syntax or format detail. Baseline 3 is appropriate.

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+resource identify: 'Beta version of ask_pipeworx: identical universal router (same 5,908 tools, same arguments, same response shape)'. It explicitly differentiates from the sibling ask_pipeworx by calling itself the experimental edge, so an agent can tell it apart from the stable router without opening the schema.

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 explicit when-to-use guidance: 'Use it exactly like ask_pipeworx when you want the newest routing' and names the alternative (the stable ask_pipeworx router) whose results it is compared against. What is missing is an explicit when-not-to-use exclusion (e.g., 'for stable behavior use ask_pipeworx'), so it stops short of a full 5.

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