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

Annotations already declare the safety profile (read-only, idempotent, non-destructive), so the description's job is to add behavioral context — and it delivers richly. It discloses that behavior is versioned: candidate routing improvements are enabled live whenever under test, that no candidate is currently active (retired on outcome evidence 2026-07-26), and that the tool is a full working router rather than a fallback stub. It also surfaces the meta-purpose (A/B comparison against the stable router to decide merges), which no annotation could convey. No contradiction with annotations.

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, front-loaded with the identity statement ('Beta version of ask_pipeworx') before any nuance. Every sentence earns its place: what it is, current runtime state, when to use it, and a corrective clarification that it is not a fallback. Slightly denser than strictly necessary — the retirement date and the 'Falls back to nothing' clarification could be trimmed — but nothing is wasted.

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 router with 5,798 underlying tools, the description is remarkably complete: interface parity with ask_pipeworx, response-shape parity, current behavior state, and usage condition are all covered. The absence of an output schema is mitigated by the explicit 'same response shape' parity clause. Minor gap: an agent unfamiliar with ask_pipeworx still doesn't know what a router response looks like, but the parity statement and sibling reference cover it well enough.

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 coverage is 100% — all six parameters (question plus five aliases q, text, input, query, prompt) are documented inline, with the question parameter itself enumerating its aliases. The description adds only the confirmation that arguments are 'identical' to ask_pipeworx, which is useful parity information but not new parameter-level meaning. Baseline 3 applies because the schema carries the semantic load.

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 precisely: 'Beta version of ask_pipeworx: identical universal router (same 5,798 tools, same arguments, same response shape)'. The verb+resource is specific (routes a question to one of 5,798 tools), and it explicitly differentiates itself from the stable sibling ask_pipeworx and the experimental 'experimental edge' framing. An agent can immediately distinguish this from ask_pipeworx and ask_pipeworx_grounded without inspecting schemas.

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 when-to-use condition: 'Use it exactly like ask_pipeworx when you want the newest routing'. It also names the comparison context (results compared against the stable router) and notes the current equivalence to ask_pipeworx. It stops short of an explicit exclusion such as 'for production decisions use the stable router,' but the beta/experimental framing plus the named sibling make the alternative obvious.

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