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

Annotations cover safety (readOnly, idempotent, not destructive), so the description's burden is reduced. It adds meaningful behavioral context beyond annotations: candidate routing improvements are enabled live during tests, no candidate is currently active, results are compared against the stable router to decide merges, and the tool is fully functional rather than a stub. It does not detail potential variability in outputs or error behavior, but the experimental nature is clearly communicated.

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 description is a compact, information-dense block that front-loads the core identity ('Beta version of ask_pipeworx: identical universal router') before moving to experimental status, current state, and usage instructions. Every sentence earns its place; there is no padding or redundancy.

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 that delegates to 5,743 tools, the description provides essential context: identical arguments, identical response shape, current parity with the stable router, and the purpose of running experimental candidates. The absence of an output schema is mitigated by pointing to ask_pipeworx's response shape. It does not detail error handling or rate limits, but the key operational context is sufficiently covered for an agent to call and interpret the tool correctly.

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%, with all six parameters documented as aliases for 'question'. The description adds no parameter-level semantics beyond the schema, only stating 'same arguments' generically. Since the input schema already fully describes the parameters and their aliases, the baseline of 3 applies; no extra value is lost but none is added.

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 identifies the tool as a beta version of ask_pipeworx and characterizes it as a 'universal router' with the same 5,743 tools, arguments, and response shape. This gives a clear functional identity and distinguishes it from the stable sibling by emphasizing its experimental 'edge' status. However, it relies on the reader already knowing what ask_pipeworx does, and the core action is only implied through the reference to a router rather than stated directly.

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 explicitly instructs when to use this tool: 'Use it exactly like ask_pipeworx when you want the newest routing'. It names the alternative (ask_pipeworx), explains the comparison and merge process, and clarifies that it is a full working router with no fallback. This leaves no ambiguity about when to prefer this beta over the stable sibling.

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