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

Annotations already declare readOnly/idempotent/non-destructive, but they say nothing about failure modes. The description discloses the full return contract (answer, evidence, confidence, source, fetched_at) and enumerates every refusal_reason and the llm_error refusal_cause taxonomy, including a time-budget 'wall' case — behavior an agent could not otherwise anticipate.

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?

Front-loaded with the differentiator, then conditional usage, then contract, then cost — a sensible priority order with no filler. The refusal_reason/refusal_cause enumeration is dense (nested quotes and parentheticals) and slightly slows scanning, but every clause carries information an agent needs.

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 must carry the return contract itself — and it does, including success shape, refusal shape, and error sub-causes. For a router-backed tool with openWorld routing over thousands of sources, the cost tradeoff and the prefer_tool escape hatch are also covered.

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 every alias plus prefer_tool is already documented in the schema, including the refusal-on-unknown-name rule. The description only adds the passing note that arguments are still filled from your question, which is marginal value over structured fields. Baseline 3 applies.

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?

Names a specific mode (hallucination-resistant grounded answering) and spells out the mechanism: same router as ask_pipeworx, but extraction constrained to the tool result. It explicitly distinguishes itself from its closest sibling (ask_pipeworx) and even from the beta variant by scope, so an agent can pick it without opening a 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?

Gives both directions of the decision: 'Use whenever an answer will be quoted, cited, or acted on' plus concrete examples (financial verdicts, legal claims, medical lookups), and the counter-case 'prefer ask_pipeworx for casual lookups' with the reason (one extra LLM call). No inference required.

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