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

The description goes far beyond the annotations by detailing exact return shapes, refusal reasons, the evidence extraction behavior, and the constraint that answers come only from tool results. It also discloses the cost tradeoff. This adds valuable behavioral context that readOnlyHint and openWorldHint do not convey.

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 longer than average but earns its length: it front-loads the core differentiating behavior, then adds return contract, refusal reasons, usage context, and cost. The first sentence is immediately informative, and no sentence is filler. It could be marginally tightened, but every clause carries useful signal.

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?

With no output schema present, the description compensates by explicitly defining the success return object and the explicit refusal object with all possible refusal reason values. It covers the tool's safety guarantees, cost, routing behavior, and usage boundary. An agent has everything needed to invoke it correctly and interpret results.

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 documents all seven accepted parameter names as aliases for 'question' at 100% coverage, so the description does not need to explain them. Because the schema fully defines parameters, the baseline of 3 applies; the description adds no additional parameter-level meaning.

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 label ('Hallucination-resistant answer mode for high-stakes reads') and describes a precise workflow: route, fetch, then extract using only the tool result. It clearly distinguishes itself from ask_pipeworx by stating it adds an extraction step and returns grounded evidence.

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 guidance is provided: use it when answers will be quoted, cited, or acted on, and when inventing facts is unacceptable. It also names the alternative (ask_pipeworx), explains the extra LLM call cost, and says to prefer the sibling for casual lookups. This leaves no ambiguity about when to choose this tool.

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