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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false, and the description adds substantial behavior beyond them: the exact success return shape, the explicit refusal contract with its full refusal_reason enum ('not_in_source'|'no_tool_match'|'tool_error'|'data_truncated'|'llm_error'), the grounded-extraction guarantee, and the extra LLM call cost. No contradiction with annotations.

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 (roughly 130 words) but every sentence earns its place: it moves logically from purpose to mechanism to return contract to refusal contract to usage guidance to cost tradeoff. It is front-loaded with the core differentiator. Slightly long, but the information density justifies the length.

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 complex QA tool with no output schema, so the description must document the return contract itself — and it does, completely: success payload, refusal payload, and refusal_reason enum values. Combined with annotations covering the safety profile (read-only, idempotent, non-destructive, open-world), nothing an agent needs to invoke it correctly or interpret its result 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% and the schema already documents the question parameter and its five aliases thoroughly. The description adds mild context — that the question drives routing across 5,908 tools and gets filled into arguments — but provides no parameter-specific syntax or formatting details beyond the schema. Baseline 3 is appropriate when the schema carries the semantic load.

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 opens with a specific, differentiating claim: 'Hallucination-resistant answer mode for high-stakes reads.' It names the verb (answer), the resource (Pipeworx data across 5,908 tools and 1540 sources), and the distinguishing mechanism (extracts the answer using ONLY what the tool result contains). It explicitly contrasts with the sibling ask_pipeworx ('Same routing... then EXTRACTS'), so an agent can tell them apart without opening the schema.

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?

Usage guidance is explicit and actionable: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete high-stakes domains listed (financial verdicts, legal claims, medical lookups, public statements). It also names the alternative and the tradeoff: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' Both when-to-use and when-not-to-use are stated.

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