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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the bar for additional disclosure is high. The description clears it easily: it reveals the exact success return shape, the refusal behavior with all five enumerated refusal_reason values (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), the cost implication (one extra LLM call), and the internal routing behavior (picks from 5,798 tools across 1,517 sources). The honest refusal path is especially valuable — it tells the agent the tool will say 'no' rather than guess. 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 but every sentence earns its place: mode definition, routing mechanics, success/refusal contract, usage conditions, and cost tradeoff. It is front-loaded with the core purpose. The only trim opportunity is the fully enumerated refusal_reason list, which would be better suited to a structured output schema — but since no output schema exists, keeping the list in prose is defensible. Slightly long, but tightly organized.

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?

There is no output schema, so the description correctly carries the full return contract inline — both the success shape {answer, evidence, confidence, source, fetched_at} and the failure shape with refusal reasons. Given the tool's complexity (routing across thousands of sources, hallucination-resistance guarantees, high-stakes usage), the description covers everything an agent needs: what it does, what it returns, when to use it, what it costs, and how it fails safely. Nothing material 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 description coverage is 100%, so the schema fully documents the single 'question' parameter and its six aliases (query, q, prompt, text, input). The description adds the useful context that this parameter will be routed internally ('picks the right tool... fills arguments'), but it does not add syntax, format, or range details beyond the schema. Per the rubric, baseline 3 is correct when the schema carries the 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 states a specific verb ('answer'/'extracts the answer'), a resource (Pipeworx routing across 5,798 tools), and a distinguishing mode ('Hallucination-resistant answer mode for high-stakes reads'). It explicitly differentiates from the sibling ask_pipeworx by naming the exact mechanical difference: 'EXTRACTS the answer using ONLY what the tool result contains.' An agent can confidently tell this apart from ask_pipeworx and ask_pipeworx_beta without inspecting 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?

Provides explicit when-to-use conditions: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with concrete domains (financial verdicts, legal claims, medical lookups, public statements). It also names the alternative and gives the cost-based selection rule: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' This is the strongest possible usage guidance — it tells the agent both when to pick this tool and when to pick its sibling.

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