ask_travel_expert

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

There are no annotations, so the description carries the full burden of disclosing behavior. It mentions 'expert answers with current information,' hinting that the tool accesses up-to-date data, but it does not disclose whether this is read-only, what the response format is, whether there are limitations or rate limits, or any side effects. For an unannotated tool, this is insufficient behavioral detail.

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 a single, efficient sentence with no filler. The core action ('Ask any travel question') is front-loaded, and the supporting detail ('expert answers with current information') follows naturally. Every word contributes to the tool's purpose.

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 single-parameter tool with no output schema, the description covers the basic call pattern (ask a question, get an answer) but lacks essential context: no mention of how the answer is presented, whether the question must be in a particular language or format, or what happens if the question is out of scope. An agent can likely invoke it correctly, but there are gaps in completeness.

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?

The input schema already documents the 'question' parameter with 100% coverage, providing the baseline of 3. The description adds a list of example topics (destinations, visas, safety, tips), which reinforces the meaning but does not fundamentally extend beyond the schema's own 'Travel-related question' description.

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 a specific verb and resource: 'Ask any travel question and get expert answers.' It enumerates topic areas (destinations, visas, safety, tips) and the general scope ('any travel question') differentiates it from the sibling tools, which handle specific tasks like itineraries or weather. This makes it unambiguous what the tool does.

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 implies broad utility ('Ask any travel question') but does not explicitly state when to prefer this tool over siblings, nor does it provide exclusions or alternatives. An agent must infer that general Q&A belongs here, while specific tasks belong to sibling tools. There is no clear when/when-not guidance.

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