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

The description discloses grounded extraction, exact success and refusal return shapes, refusal reason enums, and the extra LLM-call cost. This meaningfully extends the read-only and idempotent annotations, and there is no contradiction with them.

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 front-loaded with the tool's purpose and risk profile, then efficiently covers success/failure behavior, usage conditions, and cost. Every clause earns its place; the detail about return shapes is necessary because there is no output schema.

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?

For a grounded Q&A tool with no output schema, the description is complete: it explains what the tool does, what it returns on success, how it signals refusal, when to choose it, and what the trade-off is versus the sibling tool. An agent has enough to invoke it correctly and interpret its result.

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% and the schema already explains the single natural-language question parameter and its aliases. The tool description does not add parameter-level details, but none are needed because the schema carries that 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 mode ('hallucination-resistant answer mode for high-stakes reads') and distinguishes it from ask_pipeworx by explaining it extracts the answer only from fetched tool results. It also conveys the scope (routing across thousands of sources) and return shape, so an agent can tell this apart from sibling tools.

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 usage guidance: use when an answer will be quoted, cited, or acted on and facts must not be invented, and prefer ask_pipeworx for casual lookups because this mode costs an extra LLM call. It also names the alternative tool directly.

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