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

Annotations only cover read-only/idempotent/open-world safety, but the description goes far beyond: it discloses the success payload shape ({answer, evidence, confidence, source, fetched_at, refusal_reason}), the full refusal taxonomy, and even the nested 'llm_error' refusal_cause values ('wall' vs 'route'|'threw'|'unparseable'|'wall_after_failure'). It also flags the extra LLM call cost and the time-budget failure mode — behavior an agent could not infer from any structured field.

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 core differentiator ('Hallucination-resistant answer mode') and tightly packed with decisions-relevant facts; almost no filler. It loses a point for the dense nested refusal_cause parenthetical, which is hard to parse in one pass and could be cleanly split.

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, yet the description fully specifies the return contract, the refusal contract, and the failure-mode causes — everything an agent needs to interpret a response. It also explains the routing internals and cost so the caller understands latency and billing implications.

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% — question and all seven aliases are documented in-schema, and prefer_tool carries its own precise description, so the schema does the heavy lifting. The description adds routing context ('picks the right tool from 7,130 across 1852 sources, fills arguments') but never addresses prefer_tool as an override or how the question interacts with it, so it stays at the baseline 3.

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 verb+resource behavior — a grounded answer mode that routes to one of 7,130 tools and extracts the answer only from the tool result — and explicitly distinguishes itself from the sibling ask_pipeworx ('Same routing as ask_pipeworx'). An agent can tell immediately that this is the strict-extraction variant rather than the casual lookup variant.

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?

Usage is stated positively ('Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts'), with concrete example domains (financial verdicts, legal claims, medical lookups, public statements), an explicit exclusion ('prefer ask_pipeworx for casual lookups'), and the cost tradeoff ('one extra LLM call') that drives the decision.

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