sbb-mcp

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

Annotations already indicate readOnly, idempotent, and non-destructive behavior, so the description's burden is reduced. It adds context about pagination direction ('earlier or later') and the dependency on a prior search, which is useful. However, it does not disclose error behavior (e.g., invalid collection ID) or return format, leaving room for more transparency.

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 consists of two short sentences, with the key action and context front-loaded. Every word contributes value, and there is no redundancy or filler. It is optimally concise for the tool's simplicity.

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 tool with only two parameters, full schema coverage, and strong annotations, the description provides sufficient context about its purpose and relationship to search_connections. It does not have an output schema, but the description implies what will be returned. Minor missing details like pagination limits or response structure do not detract significantly from its 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?

Schema coverage is 100% with detailed descriptions for both parameters. The description merely echoes the schema's statement about using the collection ID from search_connections results, adding no new semantic meaning beyond what the schema already provides. Thus, the baseline of 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 action: 'Load earlier or later train connections for a previous search.' It identifies a specific resource (train connections) and scope (previous search), distinguishing it from siblings like search_connections, which creates the search, and get_trip_details, which fetches trip specifics. The phrasing is direct and unambiguous.

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 gives clear context for use: it is meant for a previous search and requires the collection ID from search_connections results. This implies the intended workflow but does not explicitly name alternative tools or state when not to use it. It provides sufficient guidance for a typical use case without exhaustive exclusions.

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 mark this as read-only and idempotent. The description adds batch limits and ID provenance constraints, which is useful beyond the annotations. No contradiction 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?

The description is three sentences, front-loaded with purpose, and every sentence adds value. No unnecessary words 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?

Given the tool's simplicity, high schema coverage, and good annotations, the description is mostly complete. However, with no output schema, it does not describe the return format, which is a minor gap.

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 already covers all parameters with descriptions and enums. The description adds meaning by clarifying reduction card options (Halbtax, GA) and specifying trip_id source, going 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 'Get ticket prices in CHF for one or more train connections' with a specific verb and resource. It distinguishes itself from sibling tools like get_ticket_link and get_trip_details by focusing on pricing.

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 gives explicit usage context: batch up to 10 trip_ids per call, use IDs from a recent search_connections result, and avoid inventing IDs. It does not mention exclusions or alternative tools, so it falls 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 readOnlyHint=true and destructiveHint=false. The description supplements this with valuable behavioral context: 'On mobile with SBB app installed, opens directly in the app with Halbtax/GA applied automatically.' This discloses environment-dependent behavior and automatic discount handling beyond what annotations provide.

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 long, front-loaded with the core purpose, and every clause earns its place. It includes a usage condition and a behavioral note with 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?

The tool has 9 parameters and no output schema, but the schema covers param semantics and annotations cover safety. The description adds usage timing and a key environmental behavior. Missing details like desktop behavior or link expiration are minor gaps, so it is adequately complete for 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 the baseline is 3. The description does not add parameter-specific semantics beyond what the schema already provides. It mentions Halbtax/GA applied automatically, which slightly relates to reduction_card, but this is behavioral context rather than parameter explanation.

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.' The verb 'get' and resource 'direct purchase link' are specific. It also distinguishes from siblings like search_connections and get_prices by noting 'Only call this when the user wants to buy a specific ticket.'

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 context: 'Only call this when the user wants to buy a specific ticket.' This clearly indicates when the tool is appropriate and implicitly excludes non-purchase scenarios. It doesn't name alternatives explicitly, but it gives a clear condition for use.

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?

The description adds that the tool returns intermediate stops, platforms, and occupancy, which goes beyond the annotations' safety profile. It also highlights the dependence on a prior search_connections call, providing useful 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 two sentences, front-loaded with the purpose and then usage. No unnecessary words or repetition; every sentence 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 one parameter fully described, rich annotations (read-only, idempotent, non-destructive), and the description covering key returned data, the tool is well-specified for an agent to select and invoke correctly. No output schema is needed for this simple detail retrieval.

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 already fully describes trip_id, and the description only restates that it comes from search_connections, adding no new meaning beyond the schema's 100% coverage. 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 retrieves detailed information about a specific train connection, listing key data (intermediate stops, platforms, occupancy). It distinguishes itself from sibling tools by focusing on trip details rather than search, pricing, or ticket linking.

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 instructs to use a trip ID from search_connections results, providing workflow context. It doesn't name alternatives but clearly implies it follows search_connections, offering clear usage context without explicit exclusions.

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?

Adds meaningful context beyond annotations: live schedules include delays/cancellations only for departures within 30 min, name resolution happens internally, and return fields are listed. This complements the readOnlyHint=true and idempotentHint=true annotations without contradiction.

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?

Four sentences, purpose first, no filler. Each sentence adds value: purpose, input handling, return contents, and live data caveat.

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?

No output schema exists, so the description appropriately details return values (departure/arrival, duration, transfers, trip IDs). It covers key behaviors like live data and internal name resolution. However, it does not mention how to get more connections or pagination limits, leaving a slight gap given the sibling get_more_connections.

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 baseline is 3. The description adds little beyond the schema: it mentions 'station names or UIC IDs' for from/to, but the schema already provides examples. No additional parameter meaning is given.

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 opens with a specific verb and resource: 'Find train connections between two Swiss stations.' It clearly differentiates from siblings by noting it returns trip IDs for downstream pricing/details/ticket calls, positioning it as the entry point for connection searches.

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?

Provides clear usage context: accepts station names or UIC IDs directly, so no prior station lookup is needed. Mentions that trip IDs feed downstream calls, implying a workflow, but does not explicitly name alternatives or exclusions like 'use search_stations for station lookup.'

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 and idempotentHint, covering safety. The description adds behavioral context by noting that it returns UIC IDs used by other tools and mention of disambiguation between matches. It does not discuss pagination or rate limits, but for a simple lookup, this is sufficient.

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 main purpose, and every sentence adds value. It includes purpose, return format, and usage guidance without 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?

For a simple, read-only lookup tool with complete annotations and schema coverage, the description fully covers purpose, usage, and return format. It clarifies when it is needed despite search_connections accepting names directly, making it contextually complete.

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 parameters are fully documented in the schema. The description does not add extra semantics beyond the schema; the example UIC ID is about return value, not parameter meaning. Thus, baseline score of 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 also specifies the output (UIC station IDs) and differentiates it from sibling search_connections, making its purpose unambiguous.

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?

Explicit usage guidance is provided: 'search_connections accepts station names directly, so this tool is only needed when the user explicitly asks for station info or when you need disambiguation between multiple matches.' This states when to use and when not to use, naming the alternative.

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