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

The description goes far beyond the annotations by disclosing the exact success return shape, the refusal contract with enumerated refusal_reason values, the constraint that evidence comes only from the tool result, and the extra cost. There is no contradiction with the readOnly/idempotent 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?

Three sentences carry a high density of useful information: what the tool does, what it returns, when to use it, and when not to use it. Every sentence earns its place, and the most important trait (hallucination-resistant grounded mode) is front-loaded.

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 spells out the full success and refusal response shapes, including the refusal enum. It also covers the key operational trade-off (one extra LLM call) and the sibling boundary with ask_pipeworx. For a tool of this complexity, nothing critical 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?

The input schema already provides 100% coverage for the question parameter and its aliases, so the description does not need to repeat parameter details. The description adds some useful context about automatic routing and argument-filling, but it does not add meaning about how the question itself should be phrased beyond what the schema states. Baseline 3 is appropriate.

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 names a specific behavior: a hallucination-resistant answer mode that routes the question, fetches tool results, and extracts the answer only from that content. It also explicitly differentiates this from ask_pipeworx by calling out the grounded extraction guarantee, so an agent can pick it apart from siblings.

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?

The description gives explicit when-to-use guidance: high-stakes reads, quoted/cited/acted-on answers, and domains where fact invention is unacceptable (financial, legal, medical, public statements). It also names the preferred alternative for casual lookups, ask_pipeworx, and explains the trade-off in extra LLM cost.

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