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

No annotations provided, so description carries full burden. It explains the basic behavior (retrieve a single alert) but does not disclose potential errors, rate limits, or data freshness. For a simple read-only operation, this is adequate but not thorough.

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?

Single sentence with no unnecessary words. Front-loaded with the core action 'Get a single alert by entity id', making it immediately clear.

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 nature (single parameter, no output schema), the description adequately explains what the tool does and how to obtain the input. No major gaps.

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 describes alert_id as 'Entity id of the alert.' The description adds that the id comes from a previous alerts() result, providing contextual meaning beyond the schema's definition.

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 a single alert by entity id', specifying the verb 'Get', the resource 'alert', and that it's a single entity. It differentiates from sibling 'alerts' by noting the origin of the id from a previous alerts() result.

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?

Description explicitly suggests when to use this tool: when you have an entity id from a previous alerts() result. This gives clear context, though it does not mention when not to use it or alternatives.

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 states the tool lists 'active' alerts, which is a behavioral trait. However, it does not disclose further details like real-time nature, performance characteristics, or any side effects, which is acceptable for a simple read-only list operation.

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 a single sentence plus usage examples, front-loading the core purpose and immediately providing context. Every part is necessary and there is no redundancy or wasted words.

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 list tool with three optional parameters and no output schema, the description covers the purpose, usage context, and parameter semantics (via schema). It does not mention ordering or pagination beyond the limit parameter, but these are reasonable defaults. Overall, it is sufficiently 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% (all three parameters have descriptions). The tool description adds no additional meaning beyond what the schema already provides, so 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 explicitly states the verb 'List' and the resource 'active service alerts', with specific alert types (planned works, delays, detours, stop closures). It clearly distinguishes from sibling tools like alert_by_id, feed_summary, etc., without ambiguity.

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 concrete usage examples ('is the tram line broken?') that imply when to use the tool. It does not explicitly exclude alternatives (e.g., alert_by_id for specific alerts), but the context is clear enough for an AI agent to select appropriately.

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 full burden. It discloses that the call is lightweight and returns only counts, not full data. No side-effects or auth needs mentioned, but sufficient for a simple read operation.

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, no fluff. Purpose is front-loaded, and additional info about cost and payload is succinctly stated.

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 zero-parameter, no-output-schema tool, the description adequately describes what it does and its performance characteristics. Could mention real-time nature, but not necessary.

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?

No parameters exist, so schema coverage is 100%. The description does not need to add parameter info. Baseline score of 4 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?

Clearly states it returns counts of vehicles, trip updates, and alerts. Distinguishes from siblings like 'vehicles' and 'alerts' which return full payloads, and 'health' which is about system status.

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 mentions it's 'cheap' and 'does not return full payloads', implying it's for quick summaries. Does not explicitly name alternatives or when-not, but the context is clear.

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 clearly indicates that the tool performs a reachability check and reports age, implying no side effects or destructive actions. A small gap: it does not describe the response format, but for a health check this is acceptable.

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 that front-load the core purpose and provide actionable usage guidance. Every word adds value; no 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?

Given the tool's simplicity (no params, no output schema), the description is complete. It clearly states the tool's function, when to use it, and what it can differentiate, fully meeting the needs of the agent.

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 input schema has no parameters (0 params, 100% coverage). The description does not need to elaborate on parameters. Baseline of 4 is appropriate as the schema provides no additional meaning.

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 specifies exactly what the tool does: check if the GZM live transit feed is reachable and report its age. It distinguishes this tool's purpose from sibling tools like 'vehicles' or 'next_arrivals' by focusing on feed health rather than transit 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?

Explicitly states when to call this tool: 'Call this first if a query seems to return empty results'. It also explains the diagnostic value: distinguishing 'no vehicles right now' from 'upstream is down', which helps the agent decide next steps.

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 bears full responsibility for behavioral disclosure. It indicates that arrivals are upcoming, sorted, and that the 'minutes_from_now' field is pre-computed. It does not mention destructive behavior (none expected), rate limits, or data freshness, but the core behavior is clearly conveyed. Some minor gaps exist (e.g., whether past arrivals are excluded), but overall transparency is good.

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 extremely concise with only two sentences. The first sentence delivers the core purpose, sorting, and scope. The second sentence adds a helpful analogy and a key output detail. No information is redundant or extraneous, and the most critical facts are front-loaded.

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 that the tool has 3 parameters and no output schema, the description adequately explains the output returns a sorted list with the 'minutes_from_now' field. However, it does not describe the full output structure (e.g., route names, arrival times), which an agent might need for correct handling. The description is sufficient for basic usage but could be more complete about the return format.

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 input schema has 100% description coverage, so the baseline is 3. The description adds value by highlighting the pre-computed 'minutes_from_now' field in the output, but it does not elaborate on parameter usage beyond what the schema already states (e.g., 'stop_id' is a GTFS ID, 'route_id' filters). Thus, the description provides minimal additional semantic context for the parameters.

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 'Get', the resource 'upcoming arrivals', and the context 'at a specific stop, across all routes, sorted by predicted arrival time'. It uses a vivid analogy 'Equivalent to a digital departure board', making the purpose immediately understandable. This tool is distinct from siblings like 'trip_updates' or 'alerts', which do not focus on per-stop arrival lists.

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 implies usage for quick stop-level arrival lookups via the 'digital departure board' analogy, but it does not explicitly state when to use this tool over alternatives (e.g., 'trip_updates' for trip-level data). There is no mention of prerequisites or situations where the tool should not be used, which leaves the agent without important decision criteria.

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 present, so the description carries full burden. It describes the output but lacks details on data freshness, pagination, or rate limits. The examples hint at real-time data, but behavioral traits are not fully disclosed.

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 with no fluff. The purpose is front-loaded, followed by concrete examples. Every word 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?

Given 4 optional parameters and no output schema, the description covers the return values (times and skips) and usage scenarios. It could mention sorting or time frame but is sufficient for a list 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%, and the description adds value by linking parameters to use cases (e.g., 'line 6' implies route_id, 'stop X' implies stop_id). It does not repeat schema but enhances understanding.

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 it lists live trip updates with scheduled vs predicted times and stop-skips. It provides concrete example queries, distinguishing it from sibling tools like alerts or next_arrivals.

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 examples are given ('is line 6 delayed', etc.), indicating when to use the tool. However, it does not explicitly mention when not to use it or provide alternatives.

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 states that it returns current position, but does not disclose error behavior, authentication needs, or rate limits; adequate for a simple read 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 a single sentence that includes examples, making it slightly longer but still clear and efficiently conveying essential information.

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 (one parameter, no output schema), the description is fairly complete: it explains what is returned and how to identify the vehicle. It could optionally describe the return format, but that is often inferred.

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 describes the parameter as 'Vehicle label, internal id, or entity id.' The description adds value by giving concrete examples (e.g., 'fleet number painted on the bus, or the entity id from a previous vehicles() call'), which helps the agent understand acceptable inputs.

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 explicitly states the verb 'Get' and the resource 'single vehicle's current position', with examples of acceptable identifiers, clearly distinguishing it from siblings like 'vehicles' which returns all vehicles.

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 implies usage when you have a specific vehicle id or label, but does not explicitly state when not to use or name alternatives like 'vehicles' or 'next_arrivals' for broader queries.

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?

Discloses ordering (newest first) and limit behavior, but lacks details on rate limits, response format, or error handling. No annotations to contradict.

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?

Concise two sentences, front-loaded with purpose and usage. No redundant information.

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 basic behavior and filtering, but lacks return format details, which is important given no output schema.

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 applies. The description adds no additional semantics beyond schema descriptions.

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 lists live vehicle positions and gives example queries, distinguishing it from sibling tools like vehicle_by_id.

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 use cases ('what's running?', 'where is line X') but does not mention when not to use or alternatives.

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