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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds that it returns the restaurant's own FAQ answer, which is a read operation consistent with annotations. It also clarifies which topics are excluded, but does not disclose behavior like error handling, empty responses, or language-specific nuances beyond what the schema's lang description already provides. The description adds some context but not a significant amount beyond annotations.

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 two sentences, front-loading the primary purpose and topic list, then stating exclusions and the alternative action. No wasted words, and the critical 'not answered here' guidance is placed in the second sentence, making it prominent. It is efficiently structured for an agent to parse quickly.

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 simple read-only FAQ lookup with a constrained enum, the description covers purpose, topic scope, exclusions, and directs to the booking page for unhandled queries. The lang parameter behavior is fully documented in the schema, so no further explanation is needed. It does not mention return format or error cases, but these are minor for a tool with such a narrow scope and no output schema. Overall, it is sufficiently complete.

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 50% (lang has a rich description, topic has only an enum). The description lists the same topics as the enum, adding no new meaning to each topic. However, it does clarify that the answer is from the FAQ and explicitly states that opening hours, lunch, and days off are not covered, which helps an agent decide whether to use this tool for a given question. The lang parameter is already well-documented in the schema, so the description doesn't need to compensate much. Overall, it adds marginal value.

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 clearly states that the tool returns the restaurant's own FAQ answer for one of nine specific topics, listing them explicitly. It also explicitly says what it does NOT cover (opening hours, lunch, days off) and directs the agent to the booking page as an alternative. This distinguishes it from siblings like get_booking_link, which likely provides the booking page, and list_courses/recommend_course, which are for different purposes.

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 when-not-to-use guidance by listing excluded topics and telling the agent to point the guest to the booking page. It does not mention the other sibling tools (list_courses, recommend_course) but those are clearly for different concerns (courses vs. FAQ). The main use case is implicit from the topic list, so it is clear enough.

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