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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the bar is lower, but the description adds genuinely useful temporal context that structured fields cannot capture: candidates are 'enabled live whenever one is under test,' none is active right now (last retired on outcome evidence 2026-07-26), and it currently 'matches ask_pipeworx exactly.' This discloses that the tool's behavior can asynchronously diverge from its sibling — exactly the kind of experimental/versioned behavior an agent needs to know.

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 sentences each carry a distinct payload: identity, current state with evidence date, usage instruction, and fallback clarification. The information density is justified by the tool's unusual beta status, though the 'identical / matches ask_pipeworx exactly / Use it exactly like ask_pipeworx' point is made three times with minor redundancy. Structure is front-loaded, leading with identity before caveats.

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 parameter, 100% schema coverage, and full annotations, the description covers identity, current behavior, usage conditions, safety, and addresses the response shape by cross-referencing 'same response shape' as ask_pipeworx. The only gap is the absence of detail about behavior when routing fails or no tool matches, which is minor given the simple parameter surface and the explicit cross-reference to a well-known sibling.

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, including the five aliases (q, text, input, query, prompt) and question, are documented in the input schema itself with an explicit alias list, so the baseline is 3. The description's 'same arguments' reference to ask_pipeworx adds only marginal cross-tool context and no new syntax or format detail beyond what the schema already provides.

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 opens by defining the tool as a 'Beta version of ask_pipeworx: identical universal router (same 5,798 tools, same arguments, same response shape),' naming a specific resource and scope in concrete terms. It clearly distinguishes this tool from the stable sibling ask_pipeworx by its experimental status and explains the operational difference: candidate routing improvements are 'enabled live whenever one is under test.' An agent can tell this apart from the sibling ask_pipeworx and ask_pipeworx_grounded without opening either 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?

The description gives an explicit selection condition: 'Use it exactly like ask_pipeworx when you want the newest routing.' It also states the evaluation purpose ('results are compared against the stable router to decide what merges') and the fallback clarification ('this IS a full working router'), which preempts the misconception that the beta might be a stub. The when-not-to-use alternative is implied by naming the stable router and the experimental edge framing.

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