Dodávky Znojmo

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

With no annotations, the description carries the full behavioral burden. It usefully discloses two non-obvious traits: fuzzy matching acceptance and an automatic 15% safety reserve that alters results. But it omits how drivers_license filters the recommendations, whether real availability is consulted, and what the response contains.

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?

Three short sentences with the purpose front-loaded and the fuzzy-matching capability emphasized in caps. Some redundancy with the schema's examples, but nothing is wasted or buried.

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 six-parameter, all-optional tool with no annotations and no output schema, the description should clarify what happens when only some inputs are supplied (e.g., weight alone) and how the driver's license constrains results. It covers the core purpose and two behavioral quirks but leaves these gaps for an agent to guess.

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 100%, so the baseline is 3. The description reaffirms that cargo_description ('2kk byt', '10 palet', 'lednice') can replace the dimension parameters, but the schema's own cargo_description field already lists those exact examples, so the added meaning is marginal; the drivers_license parameter is never explained behaviorally.

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 states a specific verb and resource: recommending suitable vehicles based on cargo dimensions and weight. It is clearly distinct from siblings like check_availability and create_booking, though it never explicitly names those alternatives. The scope is understandable without opening the schema.

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: call this when you have cargo dimensions/weight and want vehicle recommendations, and fuzzy text input is explicitly permitted as a substitute for exact dimensions. However, there is no statement of when NOT to use it, and no pointer to check_availability for actual availability or create_booking for the next step.

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

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

With no annotations, the description carries the full behavioral burden. It does add real value by disclosing the pricing rules (21% VAT, 500 km/day included, 3.50 CZK/km over-limit), but it never states that the call is read-only, what the response contains, or whether the quoted price is per vehicle or aggregate.

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?

Two tight sentences with the core capability front-loaded and the pricing policy following as supporting detail. Nothing is redundant or padded.

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 should clarify what 'dostupnost' returns — a boolean, a list of available vehicles, or a price quote — especially given the optional vehicle_id. It is adequate for a simple check but leaves the return shape and the no-vehicle_id behavior ambiguous.

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% and all three parameters are documented in the schema, so the baseline is 3. The description's mention of 'zadaném období' loosely maps to from/to but adds no format or semantics beyond what the schema already provides, and it says nothing about what happens when vehicle_id is omitted.

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 states a specific verb and resource: it checks vehicle availability for a given period and computes the total rental price including 21% VAT. That is clearly distinct from create_booking, get_fleet_info, and calculate_load_compatibility, though the description never names a sibling to reinforce the distinction.

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 only implied — 'v zadaném období' suggests this is the pre-booking availability/price check, but the description never says when to use it instead of create_booking or get_fleet_info, nor does it state any prerequisites.

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

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

With no annotations, the description carries the full disclosure burden. It does add genuine behavioral context: incomplete data is accepted and missing fields are prompted for in conversation, which is non-obvious for a create tool. But it says nothing about side effects, permission requirements, conflict handling with existing reservations, or what the call returns.

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?

Two tight sentences with no waste; the core action is stated first and the incomplete-data behavior follows. Slightly more structure (e.g., naming prerequisites) would be needed for a 5.

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 7-parameter mutation tool with no annotations and no output schema, the description covers the most important quirk (partial input accepted) but leaves out return behavior, conflict/availability implications, and any permission context. Adequate but with clear gaps given the tool's complexity.

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 100%, so all seven parameters (dates, contact fields, vehicle_id) are already documented in the schema. The description adds no format, constraint, or inter-parameter detail beyond that, so the baseline 3 applies.

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 names a specific verb and resource ('Vytvoří novou rezervaci' – creates a new reservation), so the agent knows exactly what the tool does. However, it offers no differentiation from siblings such as check_availability or calculate_load_compatibility, which could plausibly be confused with booking-flow steps.

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?

It implies the conversational context ('chybějící pole si vyžádá od uživatele v konverzaci'), which tells the agent it can call this even with partial data – useful implied guidance. But it never states when to prefer this over check_availability or what prerequisites must hold before creating a booking.

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

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

No annotations are provided, so the description carries the full burden. The framing ('Vrátí' — returns) implies a side-effect-free read, which is helpful, but it says nothing about caching, freshness of the data, response format, or failure behavior. For a trivial no-param getter the risk is low, so a middle score is fair.

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?

A single front-loaded sentence with the verb and resource first and the returned fields listed after. No filler, no redundancy.

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?

There is no output schema, so the description's enumeration of return fields (phone, email, address, hours, map) is the only disclosure of what comes back — and it covers that well. Minor gap: no indication of whether the map is a URL, coordinates, or an embedded object.

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 schema has zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description wisely spends its words on the return contents instead.

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 uses a specific verb ('Vrátí' / returns) plus a resource ('kontaktní údaje půjčovny') and enumerates the returned fields (phone, email, address, opening hours, map). It does not explicitly differentiate itself from the siblings, but the resource is distinct enough that confusion with get_fleet_info or check_availability is unlikely.

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?

No explicit statement of when to use this versus alternatives; the usage is implied by the resource name alone. For a zero-parameter info lookup this is adequate, but there is no guidance such as 'use when the customer asks for location or hours' or a note that other tools supply fleet/booking data.

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

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

No annotations are provided, so the description carries the full burden. It does add a genuine behavioral fact — 'Data jsou v reálném čase z databáze' (real-time data) — which tells the agent results are live rather than cached. It says nothing about read-only semantics, authentication, rate limits, result size, or pagination, which is a notable gap with zero annotation coverage.

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?

Two short sentences with zero filler, front-loading the resource and then the freshness attribute. Every clause earns its place.

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 and no annotations, the description partially compensates by naming the returned fields (specs, dimensions, prices) and the data freshness. It still leaves the response shape unclear (single record vs. full list) and does not state that omitting 'category' returns the whole fleet.

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 100% and the single optional enum parameter is fully self-documenting, so baseline 3 applies. The description lists what kind of data is returned but says nothing about how the 'category' filter behaves (e.g. omitted = all vehicles), adding no meaning beyond the schema.

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 ('Získá kompletní informace o vozovém parku') and enumerates the payload (technical parameters, dimensions, prices), so the agent knows exactly what comes back. It does not name or contrast any sibling, but the siblings (booking, availability, load calculation, contacts) are far enough apart that confusion is unlikely.

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?

There is no when-to-use guidance, no prerequisite, and no mention of alternatives such as check_availability when the agent actually wants date-specific availability. The agent must infer that this is the static catalogue lookup; nothing in the text states that.

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