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

Excellent disclosure beyond the annotations: it reveals the tool is a live experimental surface whose routing can change dynamically whenever a candidate is under test, discloses the current inactive state with a specific retirement date, confirms current parity with stable, and guarantees full functionality ('Falls back to nothing — this IS a full working router'). The readOnlyHint, openWorldHint, and idempotentHint annotations are consistent with a question-routing tool, and the description complements rather than repeats them.

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 dense sentences, each carrying distinct information: identity and scope, current experimental state, usage instruction, and the no-fallback guarantee. Slightly long due to the precise retirement date, but that detail substantiates the 'currently matches ask_pipeworx exactly' claim. Core identity is front-loaded ahead of the operational details.

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 dynamically experimental router, the description covers the operational essentials: what it is, scope of 5,908 tools, when behavior changes (candidate under test), current parity with stable, invocation approach, and how output is used. The implicit pointer to ask_pipeworx for response shape is a reasonable substitute for a missing output schema. Minor gap: it never specifies what kinds of candidate routing improvements might appear while under test.

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%, with all six parameters documented as aliases for the single required 'question' field. The description adds only that the tool takes the 'same arguments' as ask_pipeworx, which orients the agent but does not deepen parameter understanding. Baseline 3 is appropriate because the schema already carries the semantic weight.

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 universal router that answers questions by dispatching across the same 5,908 tools as ask_pipeworx, and frames it explicitly as the experimental beta edge of that sibling. It distinguishes itself from the stable ask_pipeworx, though it leans on that sibling for the core functional definition ('identical universal router... same response shape') rather than fully stating the purpose independently.

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?

Gives explicit when-to-use guidance: 'Use it exactly like ask_pipeworx when you want the newest routing,' and explains the beta context (results compared against the stable router to decide merges). It stops short of explicit when-not-to-use exclusions, such as preferring stable ask_pipeworx for consistency or ask_pipeworx_grounded for grounded answers, leaving those to inference from 'experimental edge.'

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