recommend_softwareCall this to recommend the right FrontDesko plan and the most relevant guides for a property. Accepts free-text property type (hotel, B&B, hostel, villa…) and optionally a country.
| Name | Required | Description | Default |
|---|---|---|---|
| rooms | Yes | ||
| country | No | ||
| property_type | Yes | e.g. small hotel, B&B, hostel, villa, resort |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations include readOnlyHint: true, which implies no side effects. The description adds that it accepts free-text property type and optionally a country, which are inputs but not behavioral traits. It doesn't disclose anything beyond the schema and annotations—like whether it returns a single plan or multiple options, or whether it's a recommendation engine vs. a static lookup. Since annotations cover the safety aspect (read-only), the description doesn't need to repeat that, but it could add value by mentioning how recommendations are generated (e.g., based on property type and room count) or that it returns a set of guides. The score is adequate but could be higher with more behavioral context.
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 concise: two sentences, front-loaded with the action ('Call this to recommend...'). It gets to the point quickly. However, the mention of 'right FrontDesko plan' could be more specific (e.g., pricing page vs. plan tier), but it's efficient and clear.
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?
Given it's a read-only recommendation tool with no output schema, the description should explain what the recommendation looks like (e.g., returns a list of guides and a plan). It doesn't. The description also doesn't mention that rooms is required, which is in the schema but not in the description. For an agent, knowing that both property_type and rooms are needed is important. The missing rooms mention and the lack of output format info make it incomplete.
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 33%, meaning only property_type has a description in the schema. The tool's description mentions property_type and country but omits the rooms parameter entirely. The schema defines rooms as a number (1-1000) but doesn't explain its role. The description should mention that rooms is required and used for recommendations, but it doesn't. Given the low coverage, the description should compensate, but it only touches on two of three parameters. This is a gap.
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 it recommends a FrontDesko plan and relevant guides for a property, using a specific verb ('recommend'), a specific resource (plan + guides), and inputs (property type, country). It distinguishes itself by its purpose, though it doesn't explicitly contrast with siblings like compare_pms or search_frontdesko_docs. The purpose is clear enough for an agent to select it over seemingly unrelated tools, but it doesn't name a specific sibling to differentiate from.
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 says 'Call this to recommend...' which gives a clear context for use. However, it doesn't explicitly state when NOT to use it or mention alternatives like compare_pms (for comparing plans side-by-side) or search_frontdesko_docs (for finding guides directly). The usage context is implied but not contrasted with siblings, leaving some ambiguity about when to choose this over compare_pms.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target clearly distinct jobs—calculating savings, checking availability, comparing competitors, pricing, recommending, and searching docs. The broad search_frontdesko_docs tool can overlap with the other informational tools, but the specific descriptions make the intended choice clear.
All tool names follow a consistent snake_case verb_noun pattern: calculate_, check_, compare_, get_, recommend_, search_. There are no mixed conventions or vague verbs, making the toolset predictable and easy to scan.
Six tools is well-scoped for a hotel-software sales/support assistant. Each tool covers a distinct user need and none feel redundant with the others.
The set covers pricing, competitor comparison, documentation, live demo availability, ROI calculation, and recommendations, which are the core front-of-funnel questions. It lacks a booking or contact-sales action, but that may be intentional for a read-only informational server.