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

Annotations already cover read-only, idempotent, non-destructive, closed-world, so the description wisely spends its words on what they cannot express: answers come only from business-approved FAQs (labelled "from the business") and owner-approved website facts with evidence URLs, a false-answer fallback path exists, and answers are never composed or inferred. That grounding guarantee is exactly the behavioral context an agent needs before quoting this tool to a user.

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?

Four short sentences ordered as purpose, return contents, failure mode, then the non-inference guarantee, so the most important facts are front-loaded. Slightly redundant between "Returns only answers from the business's approved FAQs" and "Answers are never composed or inferred", though each adds a distinct constraint.

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, the description appropriately spells out the return shape: provenance labels, evidence URLs, and the answered:false case. The one gap is provenance of the `business_id` input, which for a two-required-parameter tool with no schema descriptions would be worth one clause.

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 0%, so the description must carry parameter meaning; it partially does by illustrating the style of a valid `question` ("do you take walk-ins?", "is there parking?"), conveying natural-language phrasing without stating the 3-300 character bounds. `business_id` is completely unaddressed, including where an agent obtains one, leaving real ground uncovered at 0% schema coverage.

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 verb+resource ("Asks a business a specific question") and immediately scopes it with concrete example questions, which separates it from siblings like get_business or search_local_offerings. The first sentence alone is enough to route an agent correctly.

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 example questions and the "approved FAQs / owner-approved website facts" scope clearly convey the kind of factual lookup this tool serves, and the answered:false branch tells the agent the tool will not fabricate. It never names an alternative tool or an explicit "don't use this for X" exclusion, so routing between it and get_business/report_business_facts is left implicit.

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