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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds a substantial layer beyond them: the full success return shape, the explicit refusal contract enumerating all five refusal_reason values, the 'ONLY what the tool result contains' extraction constraint, and the extra-LLM-call cost. No contradiction with annotations; the refusal-on-no-match behavior actually enriches the readOnlyHint.

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?

Three dense sentences, each earning its place: mechanism+return shape, refusal behavior, and usage guidance+cost tradeoff. The key differentiator ('Hallucination-resistant... high-stakes reads') is front-loaded. Slightly heavy on enumerated return fields, but with no output schema that detail is load-bearing rather than redundant.

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?

This is a high-complexity tool (5,908-source router, multi-mode failure behavior, cost tradeoff, no output schema), and the description covers every decision an agent needs: when to select it, what response shape to expect in both success and refusal cases, and what invoking it costs. The missing output schema is fully compensated by the documented return format. The only conceivable gap — how ask_pipeworx_beta differs — belongs to that sibling's own description.

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% — the schema fully documents question and its five aliases (q, text, input, query, prompt) as 'Your question in natural language.' The description adds only indirect context ('fills arguments' during routing) rather than parameter-specific detail, which is appropriate since the schema carries the full burden. Baseline 3 applies.

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?

States a specific verb+resource: a 'hallucination-resistant answer mode' that routes across 5,908 tools then extracts answers using ONLY the tool result. It explicitly names the sibling it is not ('Same routing as ask_pipeworx') while differentiating on the grounded-extraction guarantee. An agent can distinguish this from ask_pipeworx, ask_pipeworx_beta, and validate_claim without opening any 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?

Explicit when-to-use: 'whenever an answer will be quoted, cited, or acted on' with concrete domains (financial verdicts, legal claims, medical lookups, public statements). Explicit when-not-to-use: 'prefer ask_pipeworx for casual lookups,' backed by the cost rationale (one extra LLM call). The alternative is named directly, leaving nothing to inference.

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