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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description goes further by documenting the full return shape, every refusal_reason value, and the refusal_cause sub-reasons for llm_error — genuinely useful behavior beyond structured fields. However, it never states latency expectations beyond the vague 'one extra LLM call', nor rate limits, nor what happens to partial evidence on refusal; and the refusal_cause enumeration is more spec dump than decision-relevant. Strong additions, but not fully rounded.

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 value proposition and the sibling contrast, then usage guidance last — a sensible order for a long description. The refusal_cause parenthetical ('wall' vs 'route'|'threw'|'unparseable'|'wall_after_failure') is dense internal jargon that costs more reading effort than it returns for tool selection.

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?

No output schema exists, and the description compensates by specifying the success object and the refusal object field-by-field, which is exactly what an agent needs to handle both outcomes. Combined with 100% schema coverage on the 9 parameters, nothing essential for correct invocation 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?

Schema coverage is 100% and the schema itself documents all eight question aliases and prefer_tool in detail, so the baseline is 3. The description adds no parameter-level meaning of its own — prefer_tool is never referenced in prose even though it is the one parameter with non-obvious routing semantics.

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?

States a specific mode ('hallucination-resistant answer mode') with a concrete verb chain: routes to a tool, fills arguments, fetches data, then extracts an answer strictly from the tool result. It explicitly positions itself against its closest sibling ('Same routing as ask_pipeworx'), so an agent can distinguish the two without opening either 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 an affirmative trigger ('use whenever an answer will be quoted, cited, or acted on' with concrete domains: financial, legal, medical, public statements) and an explicit exclusion ('prefer ask_pipeworx for casual lookups'), plus the reason (one extra LLM call). This is textbook when/when-not/alternative guidance.

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