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

Beyond the annotations (readOnly/idempotent/openWorld=false), the description discloses genuinely useful behavior: trips may stop in between and partial legs of longer trips are matched, prices are per person, booking happens off-tool via booking_url with payment direct to the driver, and ambiguous city names produce candidate lists. This is exactly the context an agent needs to interpret and act on results.

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 action, then layered with geography, partial-trip matching, pricing/booking, and ambiguity handling. All sentences carry information, though the geography parenthesis and booking-flow sentence could be trimmed without losing callable guidance.

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 partly compensates by noting that ambiguous cities return candidate options and that trips include intermediate stops. It still does not sketch what a normal result contains (e.g., departure times, price fields), which is the remaining gap for a 5-parameter search tool.

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%, so all five parameters (from, to, date, seats, language) are already documented in the schema, and the baseline for high coverage is 3. The description adds only marginal parameter meaning ('prices are per person', partial-leg matching) and nothing about seat availability or how language affects results beyond the schema's own text.

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 and resource ('Search minibus trips offered on busik.ch between two cities on a given travel date') with clear scope (geography, date-bound). It is easy to distinguish from get_trip_details and get_routes_for_city by name and content, but the description never explicitly names or contrasts those siblings, so it stops short of a 5.

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?

Usage is implied rather than stated: an agent can infer 'use this when you know origin, destination and date.' However, there is no explicit when-not-to-use guidance or routing to get_routes_for_city (for browsing a city's connections) or get_trip_details (for a chosen trip), which the agent must infer on its own.

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