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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, non-destructive), so the description's job is lighter. It adds genuinely useful dynamic behavior: candidate routing improvements go live whenever under test, the last was retired, and "Falls back to nothing — this IS a full working router" disambiguates the beta status. It does not disclose rate limits, latency overhead of beta testing, or failure behavior when a candidate misroutes.

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 with the identity and current parity front-loaded before usage guidance; nothing is wasted. The precise retire date ("2026-07-26") and the parity claim repeated in sentences 1, 2, and 4 are slightly redundant and could be trimmed.

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 complex 6-parameter router with no output schema, the description covers identity, current behavior, when to use it, and the A/B evaluation context. Defaulting the response shape to "same response shape" as ask_pipeworx is reasonable but forces the agent to resolve a sibling's contract. The experimental edge and current parity are explained well enough to call the tool safely.

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%, so question and its aliases are fully self-documented; the description adds no parameter-level meaning beyond the phrase "same arguments" which only confirms parity with ask_pipeworx. Baseline 3 applies because the schema does the heavy lifting and the description does not need to compensate.

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 clearly states what the tool is: "Beta version of ask_pipeworx: identical universal router (same 5,798 tools, same arguments, same response shape)", giving a specific resource scope and distinguishing it from the stable sibling ask_pipeworx via its experimental role. However, the core action is carried by the jargon term "universal router" and reference to ask_pipeworx rather than a plain verb, so it is clear but slightly indirect.

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?

It gives an explicit selection condition: "Use it exactly like ask_pipeworx when you want the newest routing", and names the stable alternative against which results are compared. It also cautions that no candidate is active right now, so current behavior matches the stable router. It does not explicitly state when-not-to-use or mention the ask_pipeworx_grounded sibling, so it stops short of a 5.

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