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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false. The description adds substantial behavioral context beyond that: the exact return structure on success, the five explicit refusal_reason values on failure, and the guarantee that answers are extracted only from tool results (anti-hallucination guarantee). No contradiction with annotations — the safety hints align with the read-only, non-destructive behavior described.

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 dense — a single wall of text — but every sentence earns its place: purpose, mechanics, return format, usage conditions, and cost tradeoff. It's front-loaded with the core purpose before diving into details. Loses one point for being a single unbroken paragraph that could benefit from structural separation of the return-format details from the usage guidance.

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?

Despite having no output schema, the description fully explains the return values (success object with answer/evidence/confidence/source/fetched_at and the refusal object with all five refusal_reason enumerations). It covers the multi-step behavior (routing, argument filling, fetching, extraction), the cost implication, and the anti-hallucination guarantee. Nothing an agent needs to invoke it correctly is missing.

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 are documented, with the question parameter's description listing all five aliases (query, q, prompt, text, input). The description adds context about the kind of questions this mode is suited for (high-stakes, quotable) but doesn't add syntax or format detail beyond the schema. Baseline 3 is correct since the schema carries the parameter documentation burden.

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 states a specific purpose — a hallucination-resistant answer mode that routes across 5,801 tools and extracts answers using only tool results. It distinguishes from the sibling ask_pipeworx by naming the exact mechanism difference (extraction vs plain routing) and clearly labels its niche (high-stakes reads). An agent can immediately tell this apart from ask_pipeworx and ask_pipeworx_beta.

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?

Explicitly states when to use: whenever an answer will be quoted, cited, or acted on, with concrete high-stakes examples (financial verdicts, legal claims, medical lookups). Also states when not to use — 'prefer ask_pipeworx for casual lookups' — and gives the cost reason (one extra LLM call). This is textbook when/when-not guidance naming the alternative.

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