sbb-mcp

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

Annotations already declare readOnly, idempotent, and non-destructive. Description adds minimal extra behavioral context beyond the parameter dependency (collection ID). No contradictions.

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, 17 words, front-loaded with the core action. Every word earns its place 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?

Provides sufficient context for a simple pagination tool with no output schema. Could mention behavior when no more connections or invalid collection_id, but the existing information is adequate.

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 schema already explains each parameter. The description reinforces the collection_id relationship but adds no new semantic 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?

Clearly states the verb 'Load' and resource 'earlier or later train connections for a previous search'. Distinguishes from sibling 'search_connections' by specifying dependency on its results.

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?

Explicitly instructs to use the collection ID from search_connections results, providing clear when-to-use context. Does not explicitly list alternatives or when-not-to-use, but the sibling set implies limited scenarios.

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 context beyond annotations: price currency (CHF), discount support, batching limit, and input source requirement. No contradiction with annotations (readOnly, idempotent, non-destructive).

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?

Extremely concise: three sentences covering purpose, key constraints, and input prerequisites. No redundant information. Front-loaded with main action.

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 operation with no output schema, the description fully covers what the tool does, its inputs, constraints, and prerequisites. No gaps given the complexity and structured fields.

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?

Although schema coverage is 100%, the description adds meaning by explaining trip_ids source and limit, and clarifying the reduction_card enum values (Halbtax, GA). It compensates for any ambiguity in the enum labels.

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 'Get ticket prices in CHF for one or more train connections' with a specific verb and resource, clearly distinguishing it from sibling tools like get_more_connections or 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?

Provides explicit guidance: batch up to 10 trip_ids, use IDs from search_connections, do not invent IDs. Also specifies supported discount cards (Half-Fare, GA). Clearly tells when to use and what to avoid.

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 context beyond annotations: the link is a direct purchase link that opens in the SBB app on mobile with Halbtax/GA applied automatically. This enriches the readOnlyHint and openWorldHint 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?

Two sentences, concise, front-loaded with the main purpose. Every sentence adds value 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?

Covers purpose, usage guidelines, and key behavioral details. Lacks explicit mention of the return format (URL string), but given no output schema, it is reasonably complete for a link-returning 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 description coverage is 100%, so baseline is 3. The description does not add per-parameter details but provides overall contextual meaning (purchase link, app behavior).

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 provides a direct purchase link to buy a ticket on SBB.ch, which 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?

Explicitly says 'Only call this when the user wants to buy a specific ticket,' providing clear guidance on when to use. Also mentions mobile-specific behavior.

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 read only and non-destructive. Description adds behavioral details on what is returned (stops, platforms, occupancy) beyond 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?

Two efficient sentences with purpose first, then usage. No wasted words, 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?

For a simple tool with one parameter and no output schema, description covers core purpose and input source. Could mention return format but adequate.

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?

Parameter trip_id is fully described in schema. Description adds relational context linking trip_id to search_connections results, providing extra semantic value.

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?

Description clearly states 'Get detailed information about a specific train connection' listing specific elements (intermediate stops, platforms, occupancy) and differentiates from siblings like search_connections and 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?

Explicitly says 'Use a trip ID from search_connections results', guiding when to invoke. Does not explicitly mention alternatives but context implies appropriate usage.

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?

Beyond annotations (readOnly, idempotent), the description discloses important behavioral traits: name resolution happens internally, live data includes delays/cancellations for trains within 30 min, and returns trip IDs for downstream calls. 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?

The description is concise and well-structured: first states purpose, then input format, then output, then live data note. No redundant sentences; all information 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?

Despite no output schema, the description adequately explains return values (times, duration, transfers, trip IDs) and live data behavior. It does not mention pagination or limits, but the sibling get_more_connections covers that. Sufficient for an agent to use correctly.

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 each parameter has a description. The tool description adds value by clarifying that from/to accept names or UIC IDs, and provides detailed guidance on the arrival_time parameter (when to set true vs false). This improves usability beyond schema alone.

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 finds train connections between two Swiss stations. It specifies accepted input types (station names or UIC IDs) and output (live schedules with times, duration, transfers, trip IDs). This distinguishes it from siblings like search_stations (station lookup) and the downstream tools.

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 guidance on when to use the tool (finding connections) and includes specific usage rules for the arrival_time parameter (only set true when user explicitly states arrival). However, it does not explicitly contrast with siblings like get_more_connections or state when NOT to use this tool.

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 readOnly, idempotent, non-destructive. Description adds that it returns UIC IDs and is used for disambiguation, complementing well 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?

Two sentences, front-loaded with purpose, minimal waste.

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 search tool with 2 params and no output schema, description mentions output format and disambiguation use case. Could add details on return structure.

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 clear descriptions for both parameters. Description adds no extra meaning to parameters beyond schema, but links to output format.

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?

Clearly states it searches for Swiss train stations, addresses, or POIs by name, and distinguishes from sibling search_connections by noting that the latter accepts station names directly.

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?

Explicitly states when to use (user asks for station info or disambiguation) and when not (search_connections accepts names directly), and mentions output UIC IDs for other tools.

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