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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds context about pagination (earlier/later) but does not disclose additional behaviors like error handling or return format.

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 concise sentences, front-loaded with the core purpose and immediate usage hint. Every word earns its place, with no fluff or repetition.

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 pagination tool with rich annotations and complete schema, the description is sufficient. It lacks an explicit note about return structure, but that is implied as consistent with search_connections results, and the sibling tools provide context.

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%, with both parameters (collection_id and direction) well-described in the schema. The description reinforces the source of collection_id but adds no new information 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?

The description clearly states the verb 'Load' and resource 'earlier or later train connections' for a previous search, distinguishing it from sibling tools like search_connections (which performs the initial search) and get_prices/get_trip_details (which retrieve other data).

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 explicitly says to use the collection ID from search_connections results, indicating the tool is a follow-up for pagination. It doesn't explicitly state when not to use other alternatives, but the context is clear enough.

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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering safety. The description adds valuable behavioral context: batch limit of 10, support for Half-Fare and GA discounts, and the requirement that trip_ids come from a recent search_connections result. This goes beyond the annotations without contradicting them.

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 three sentences long, front-loads the core purpose, and every sentence adds information. It efficiently covers scope, discounts, batching, and input provenance without 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?

Given the simple parameter set, rich annotations (read-only, idempotent), and full schema coverage, the description is complete. It explains the price type (CHF), discount handling, batch constraints, and ID source. No output schema exists, but the description's 'Get ticket prices' clearly implies the return value, so this is sufficient.

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 covers 100% of parameters, so baseline is 3. The description adds meaning by explaining the reduction_card options ('Half-Fare card (Halbtax) and GA travelcard discounts') and by emphasizing that trip_ids must come from recent search_connections results and not be invented. This adds value over the raw 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?

The description clearly states the tool's purpose: 'Get ticket prices in CHF for one or more train connections.' It specifies the resource (train connections), the currency (CHF), and the scope (one or more). It also distinguishes itself from siblings like search_connections and get_trip_details by focusing on price retrieval and referencing trip_ids from search_connections.

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 provides clear usage context: 'Up to 10 trip_ids per call — batch them in a single request rather than calling once per connection' and instructs to use 'trip_ids from a recent search_connections result; do not invent IDs.' This gives practical guidance on batching and input source, though it does not explicitly mention alternatives or when not to use this tool relative to siblings.

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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description builds on that with useful behavioral details: automatic Halbtax/GA application and mobile app deep-linking. No contradictions with 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?

Three sentences, each serving a clear purpose: function, usage condition, and platform behavior. No redundancy or fluff.

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?

The description covers the tool's purpose, when to use it, and key behavioral nuances. With a fully documented schema and annotations, this is sufficient for an agent to select and invoke it correctly, though it does not explicitly state the return format (a link is implied).

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?

All 9 parameters are fully documented in the schema (100% coverage), so the description does not need to explain them. It adds a minor note about Halbtax/GA being applied automatically, which aligns with the reduction_card parameter, but no further parameter-specific insight.

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 the tool's function: 'Get a direct purchase link to buy a train ticket on SBB.ch'. It uses a specific verb and resource, and the focus on 'buy' distinguishes it from sibling tools like search_connections or get_prices.

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 phrase 'Only call this when the user wants to buy a specific ticket' provides an explicit usage condition. It does not explicitly name alternative tools, but the condition implies this is for purchase scenarios rather than searching or pricing.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the agent knows it's a safe read. The description adds context about the kind of details returned (stops, platforms, occupancy) but does not disclose other behavioral aspects like pagination or error handling. This meets the baseline for annotation-covered tools.

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 sentences capture the purpose and usage context with no wasted words. The description is front-loaded with the primary action and the second sentence provides essential guidance on obtaining the trip ID. It is optimally concise.

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 the low complexity (single parameter), rich annotations, and a description that lists the type of information returned, the description is complete for an agent to use correctly. It lacks an output schema but the description gives enough detail about what to expect. There is no need for additional explanation of return values because the description already enumerates examples.

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 the schema describes trip_id as 'Trip ID from search_connections results'. The description reinforces this by instructing to use a trip ID from search_connections, adding a small amount of shared context. Since the schema already carries the semantic load, this is the appropriate baseline.

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 the tool's function: 'Get detailed information about a specific train connection' with specific examples (intermediate stops, platforms, occupancy). It uses a strong verb and specifies the resource, and the mention of 'trip ID from search_connections' differentiates it from sibling tools by tying it to a prior search step.

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 provides clear context: this should be used after obtaining a trip ID from search_connections. It tells the agent when to use it, but does not explicitly state alternatives or when not to use it, so it doesn't meet the full 'when/when-not/alternatives' standard.

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?

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond this: 'name resolution happens internally' and 'Live data: includes delays and cancellations for trains departing within 30 min.' These details enrich understanding without contradicting 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 three sentences, each serving a clear purpose: what the tool does, accepted inputs, and what it returns. It is front-loaded and free of redundancy or fluff.

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?

Although there is no output schema, the description lists key return fields (departure/arrival times, duration, transfers, trip IDs) and the live-data caveat. It does not mention pagination or the existence of get_more_connections, but the description is still substantial for a search tool with this 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%, with detailed descriptions for each parameter. The main description does not add significant parameter-level meaning beyond what the schema already provides (e.g., station names/IDs are already mentioned in the schema). Baseline 3 is appropriate.

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 the tool's function: 'Find train connections between two Swiss stations.' It uses a specific verb and resource, and distinguishes itself from siblings like search_stations (which finds stations) and get_prices/get_trip_details (which are downstream).

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 positions this as the entry point for schedule queries, noting it returns 'trip IDs for downstream pricing/details/ticket calls.' This implies when to use it relative to siblings, but it does not explicitly mention alternatives or when-not-to-use, so it falls just short of a 5.

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?

Annotations already declare this as read-only and idempotent, so the description doesn't need to repeat safety traits. Beyond annotations, the description reveals that the tool returns UIC station IDs and can search addresses and POIs, adding valuable behavioral context about output and coverage. It doesn't mention ordering or pagination, but that's not critical for a simple read-only search tool.

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-loaded with the core purpose and followed by a practical usage note. Every sentence earns its place with no redundancy or fluff, making it appropriately sized and well-structured.

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?

The description fully covers the tool's scope, output (UIC IDs), and usage context, including when it should not be used. Given the simple schema and rich annotations, no additional information is necessary for an agent to correctly select and invoke the 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%, with both query and limit having descriptions in the schema. The description does not add additional parameter-level detail beyond the schema; it only mentions 'by name' which aligns with the query parameter. Since the schema already explains parameters, the description provides minimal extra semantic value, so a baseline 3 is appropriate.

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 the tool's function: 'Search for Swiss train stations, addresses, or points of interest by name.' It specifies a concrete action and resource. It also distinguishes from the sibling tool search_connections by noting that search_connections accepts station names directly, making this tool's unique purpose (station info, disambiguation) explicit.

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 provides explicit usage guidance: 'this tool is only needed when the user explicitly asks for station info or when you need disambiguation between multiple matches.' It also names the alternative (search_connections) and when to use it instead, giving clear context for tool selection.

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