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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the description's job is to add context beyond safety hints. It does: beta status, live candidate routing improvements under test, parity with the stable router as of 2026-07-26, and 'Falls back to nothing — this IS a full working router, just the experimental edge.' This last point is valuable because an agent could otherwise assume a beta tool is a stub or fallback wrapper.

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?

A compact single paragraph front-loaded with identity ('Beta version of ask_pipeworx: identical universal router'), then current state, usage instruction, and evaluation process. Concrete details like 5,908 tools and the 2026-07-26 retirement date earn their place and add precision without padding. Slightly dense, but every sentence carries information.

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 genuinely required parameter, rich safety annotations, and no output schema, the description covers identity, current behavior, usage conditions, and what happens to results (comparison against the stable router). The response shape is deferred by reference to ask_pipeworx's identical shape, which is an acceptable resolution given the sibling relationship. Minor gaps: no explicit note on when to prefer stable ask_pipeworx instead.

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 (question, q, text, input, query, prompt) are documented as aliases in the schema itself. The description adds no parameter-level detail, but the schema fully carries the burden, so the baseline 3 applies. The description's mention of 'same arguments' as ask_pipeworx adds negligible semantic value.

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 immediately identifies the tool as 'Beta version of ask_pipeworx: identical universal router (same 5,908 tools, same arguments, same response shape)', giving a specific resource and scope. It clearly distinguishes itself from siblings as the experimental edge, and the sibling list confirms ask_pipeworx exists as the stable counterpart. It relies somewhat on the reader knowing what a 'universal router' does, which keeps it from a 5.

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?

States explicitly when to use it: 'Use it exactly like ask_pipeworx when you want the newest routing; results are compared against the stable router to decide what merges.' It names the alternative (stable ask_pipeworx) and adds the current-state caveat that no candidate is active so it currently matches ask_pipeworx exactly. It does not spell out an explicit when-not-to-use case, but the stability-versus-experimental contrast is clearly implied.

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