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

With no annotations, the description carries the full burden. It discloses the read-only nature ('List') and defines the alert context, but does not mention ordering, pagination, or any side effects. Since it's a simple list operation, this is minimally adequate but lacking richer behavioral detail.

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, well-structured sentence that front-loads the action and scope. Every word adds value; no redundancy or filler.

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 one-parameter tool and no output schema, the description adequately conveys what the tool returns (a list of active alerts). It could mention result ordering or that limit controls total count, but the schema already covers the default. Overall, it's sufficient 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 coverage is 100%, so the baseline is 3. The description adds meaning to the alerts themselves but not to the 'limit' parameter, which is already well-described in the schema. No additional context needed 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 uses a specific verb ('List') and clearly identifies the resource ('currently active alerts') with an explicit definition ('stations running low on bikes or free anchors right now'). This clearly differentiates it from siblings like get_alerts_history and get_stations.

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 the tool is for real-time or current alert status, contrasting with historical alerts (get_alerts_history). However, it does not explicitly state when not to use it or name alternatives, 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?

With no annotations provided, the description carries the full burden. It explicitly discloses that requesting csv format or a limit above 500 requires BIZI_PUBLIC_API_KEY, which is a critical behavioral constraint. While it doesn't cover all possible quirks (e.g., pagination defaults), it adds meaningful context beyond the schema.

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 the core action and then the key exception. Every sentence contributes meaningful information without repetition or filler.

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 9 optional parameters and no output schema, the description covers the essential usage context: historical scope, example analysis, and authentication constraints. It doesn't describe return values, but the 100% schema coverage and focus on filters/constraints make it adequate for a query 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%, so baseline is 3. The description adds value by mapping filters to the conceptual fields (station, alert type, severity, time range) and by explaining the API key requirement for specific parameter values (limit > 500). This goes beyond what the schema alone provides.

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 the tool queries historical alerts (both resolved and active) with specific filters. The example question 'how often has station X run out of bikes' further clarifies its analytical purpose and distinguishes it from likely real-time sibling tools like get_alerts.

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 a concrete use case ('how often has station X run out of bikes') indicating when to choose this tool. However, it does not explicitly mention when NOT to use it or directly compare to alternatives like get_alerts or get_history, so it narrowly misses 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?

With no annotations, the description must disclose behavioral traits. It only states the action without mentioning side effects, return format, pagination, or data freshness. It adds minimal behavioral context beyond the basic retrieve 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, concise sentence with no wasteful words. It is front-loaded and delivers the essential information efficiently.

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 one parameter, no output schema, and no annotations, the description is minimal but adequate for a basic read operation. However, it lacks details on the exact return format, time range, or limitations, leaving some 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?

The schema describes stationId as 'Station identifier' with 100% coverage. The tool description adds no additional meaning to this parameter, so 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 retrieves occupancy heatmap cells (day x hour) for a single station, using a specific verb and resource. This distinguishes it from sibling tools like get_stations or get_rankings, which focus on 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?

The description provides no guidance on when to use this tool versus alternatives such as get_history or get_patterns, nor does it mention exclusions or prerequisites. The implied usage is clear from the verb, but no explicit context is given.

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 burden. It discloses the data scope ('since BiziDashboard started recording') and the inclusion of coverage metadata. However, it does not mention limits, pagination, or performance characteristics. It is honest about what it returns but lacks deep behavioral detail.

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 action and resource. The second sentence adds valuable context about why this tool exists relative to GBFS. No 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 tool with one optional parameter and no output schema, the description is fairly complete. It explains what data is returned (demand/balance history, coverage metadata) and the temporal scope. It could mention the default format, but the schema already documents that. Minor gaps remain about how data is structured, but overall 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?

The schema has 100% coverage of the single optional 'format' parameter, so the description does not need to add parameter details. It does not repeat or supplement the schema, and no additional parameter meaning is provided. A baseline of 3 is appropriate given the high schema coverage.

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 ('Get') and resource ('full historical daily demand/balance data') plus additional context ('coverage metadata'). It clearly distinguishes from sibling tools like get_alerts_history by specifying the data type (demand/balance) and the long-range scope.

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: it is for long-range historical data that GBFS cannot provide. This implies when to use it, though it does not explicitly name alternative tools or state when not to use it. The contrast with GBFS gives a practical alternative but not a sibling exclusion.

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 burden of disclosure. It enumerates the types of data returned (daily demand curve, flow signals, transit analysis) and adds a limitation ('usage rhythms rather than instantaneous state'). It does not explicitly state side effects or rate limits, but the tool's read-only nature is evident from the name and description, and the provided detail is substantial.

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: the first lists the tool's outputs, and the second provides a concise usage hint. Every word earns its place, and the most important information is 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?

The description fully covers the tool's purpose, output categories, and intended use case. With no output schema, it does not explain return shape, but the enumerated signal types provide sufficient context for an agent to understand the tool's capabilities. The schema covers parameters, so nothing critical is missing.

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 the baseline is 3. The description does not add additional meaning to the parameters (month, demandDays, mobilityDays) beyond what the schema already provides, but it does not need to since the schema is complete. It stays at 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 uses a specific verb ('Get') and clearly identifies the resource ('mobility signals'), breaking it down into distinct components (demand curve, flow signals, transit impact). It also distinguishes itself from sibling tools by contrasting 'usage rhythms' with 'instantaneous state.'

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 a clear use case ('understanding usage rhythms') and implicitly excludes alternative use cases via 'rather than instantaneous state.' It does not explicitly name sibling tools or provide a full when/when-not matrix, but the guidance is sufficiently clear for an agent to decide.

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 must disclose behavior itself. It mentions 'typical' and 'weekday vs. weekend' which indicates a summarized/aggregated output, but does not explain how the patterns are computed, what time range is covered, or what the response format looks like. It adds some context but not comprehensive behavioral details.

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, well-front-loaded sentence that packs the core purpose and differentiation into 17 words. No filler or redundant information; every word contributes to understanding.

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 one-parameter tool and no output schema, the description could be more explicit about what the returned data looks like (e.g., a table of hours and bike availability values). The core concept is clear, but the absence of any return-format hint leaves some gaps for an AI agent invoking 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?

The schema already documents stationId at 100% coverage. The description adds minimal value by restating 'single station' but does not provide additional meaning such as station ID format or examples. It meets the baseline but does not exceed it.

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 a specific action ('Get weekday vs. weekend hourly occupancy patterns') and resource ('for a single station'), with a concrete scope ('typical bike availability by hour'). It differentiates from sibling tools like get_history (raw history) and get_heatmap (likely aggregated heatmap) by specifying the pattern nature.

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 when to use the tool (when you need typical hourly patterns for a single station) but provides no explicit exclusions or alternatives. It does not mention when to prefer get_history or get_heatmap instead, leaving some ambiguity in tool selection.

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 is the only source of behavioral context. It explains the meaning of turnover and availability and mentions the historical scope, but omits important details like sort order direction, default limit handling, or how availability is computed.

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, front-loaded sentences with no redundant information. Every phrase contributes to the tool's purpose or use context.

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 three-parameter tool with no output schema, the description covers the core purpose and metrics. However, it lacks explicit details about return ordering (ascending vs descending), response shape, or the exact time range of 'observed history', leaving some gaps for an agent to infer.

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 the baseline is 3. The description adds value by clarifying 'turnover' as 'bike rotation activity' and linking availability to being 'reliably stocked', which enriches the enum semantics beyond the schema's single-line description.

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 ranks stations by two specific metrics (turnover and availability), using a specific verb ('Rank') and resource ('stations'). This distinguishes it from sibling tools like get_stations or get_patterns.

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 use cases ('finding the busiest or most reliably stocked stations over the observed history'), which helps an agent know when to use it. However, it doesn't explicitly name alternatives 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?

With no annotations provided, the description carries the behavioral disclosure burden. It clearly states the output contents, the optional filter, and the auth prerequisite for certain options, implying default json format and ≤30-day windows. It doesn't cover error handling, but the disclosed constraints are meaningful and not contradicted by any 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 a single, well-organized sentence that front-loads the primary purpose, then adds output details, filtering options, and prerequisites in a logical order. There is no redundancy or filler, and every phrase contributes useful 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 has three optional parameters, no output schema, and no annotations, the description covers the main purpose, report contents, optional filtering, and auth constraints—sufficient for most use cases. It omits default day values (present in schema) and exact error behavior, but the missing details are not critical for a well-formed definition.

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 the description doesn't need to re-explain parameters. It adds a bit of context (district filter is optional, csv and days>30 require API key), but these are already reflected in the schema. The description does not introduce new parameter meaning beyond what the schema provides.

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 ('Get') and identifies a clear resource ('station rebalancing diagnostic report'), then elaborates with detailed output components (per-station classification, risk predictions, transfer recommendations). This level of specificity clearly distinguishes it from sibling tools like get_stations or get_rankings.

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 solid context for usage, including optional district/barrio filtering and explicit API key requirements for csv format or windows above 30 days. However, it doesn't name alternative tools or explicitly state when not to use this tool, so it stops short of full guidance.

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 burden of behavioral disclosure. It clearly states that data is a snapshot and not real-time, which is a non-obvious limitation. It also implies a read-only 'list' operation. This is good, though it does not mention response size, pagination, or potential errors.

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 the main purpose, followed by a concise caveat about data timeliness. 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?

The description explains what the tool returns (station list with availability fields) and adds a freshness caveat. There is no output schema, so this is sufficient for a simple listing tool. Missing details like sorting or station count are minor.

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 only parameter, 'format', has a complete schema description ('Response format. Defaults to json.') with an enum. Since schema coverage is 100%, the description does not need to add anything. The tool description does not mention parameters, but the schema already fully accounts for them.

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: 'List every Bizi Zaragoza station.' It also enumerates the included data (bikes available, free anchors, capacity, location), making the tool's purpose immediately clear and distinct from sibling tools like get_rankings or get_alerts.

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 useful context about data freshness ('latest known availability snapshot', 'not necessarily real time'), which helps an agent decide if this tool is appropriate. However, it does not explicitly mention when to use this tool over siblings or exclude any cases.

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