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

No annotations are present, so the description must carry behavioral disclosure. It specifies that only active alarms are listed and gives examples of alarm types, which adds context beyond the name. However, it doesn't disclose output structure, ordering, permissions, or limits.

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 that front-loads the verb and resource, then notes filtering options. 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?

The tool is a straightforward read operation with all input parameters documented in the schema. The description doesn't explain the return format, but the examples of alarm types partly compensate for the absent output schema. It lacks details on pagination or error handling, but overall is adequate for a simple 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?

All four parameters have thorough schema descriptions, achieving 100% coverage. The description's mention of filtering by severity, type, and device mirrors the schema without adding new syntax or default behavior information.

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 the specific verb 'List' and identifies the resource as 'active security alarms from Firewalla', with examples that distinguish it from sibling tools like get_devices or get_top_talkers. It clearly states the tool's scope and filtering capabilities.

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?

No explicit mention of when to use this tool over alternatives or exclusions. The description implies usage for retrieving security alarms, but doesn't reference sibling tools or provide decision 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 transparency burden. It accurately conveys the read-only nature by saying 'shows' and describes the output content (blocked/allowed decisions and reasons). However, it does not disclose limitations like data retention, output limits, or error conditions, leaving some gaps.

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-loads the primary purpose, and adds essential filtering detail without any waste. Every clause contributes value, 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?

For a simple read-only log retrieval tool with no output schema and moderate parameter count, the description provides sufficient context: it explains what the logs contain, the filtering options, and the purpose. It could mention counting or ordering, but the schema handles parameter details, and the sibling context makes the tool's role clear.

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 for all five parameters, so the baseline is 3. The description adds a high-level summary of filtering dimensions (MAC, domain, IP, time range) that maps to the schema, but it does not add new meaning beyond what the schema already provides. Count is not mentioned, but the schema covers 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 the verb ('Get') and resource ('audit logs') and specifies the scope: blocked and allowed traffic decisions. It distinguishes itself from siblings by focusing on firewall rule outcomes, which is unique among the listed tools like get_dns_queries or search_flows.

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 when to use the tool—when investigating blocked connections and why they were blocked. It also lists key filters (MAC, domain, IP, time range) that help narrow usage, though it does not explicitly mention alternative tools or 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?

With no annotations, the description carries the burden of behavioral disclosure. It indicates a read-only 'get' operation, but it does not clarify whether 'connected devices' includes only currently online devices or all known devices, nor does it disclose any other behavioral details. The ambiguity with sibling tools like get_offline_devices leaves a gap, though the read-only nature is evident.

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, with two short sentences. The second sentence 'Shows which devices are on each network' is somewhat redundant with the first but adds a minor clarification about the output orientation. It could be trimmed, but it is not verbose and the key 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?

For a simple read tool with one optional parameter and no output schema, the description provides adequate context to understand the grouping function. However, it could benefit from clarifying the inclusion criteria (online vs. all devices) and the return format, especially given the presence of sibling tools like get_offline_devices. This slight gap keeps it from a 5.

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 provides a complete description for the single 'count' parameter (default 500, max 5000). The description text itself adds no parameter-specific meaning beyond the schema, so the baseline of 3 applies due to 100% 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 clearly states the tool's function with the specific verb 'Get' and identifies the resource as 'connected devices grouped by network segment/VLAN'. This explicitly distinguishes it from sibling tools like get_devices and get_vlans, and the second sentence reinforces the grouping behavior.

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 a per-network view of devices is needed, but it does not explicitly state when to use this tool vs. alternatives like get_devices or get_offline_devices. No exclusions or alternative conditions are mentioned, but the clear context of grouping provides a reasonable usage signal.

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 available, so the description carries the burden of behavioral disclosure. It states that the tool returns flow data from the Firewalla init payload, which provides some context, but it does not mention safety, permissions, limitations, or side effects. For a simple read operation, this is minimally 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?

The description is two sentences long, front-loaded with the purpose, and contains no extraneous information. It efficiently conveys the tool's function and data source.

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 a single parameter and no output schema, so the description needs to explain the return value. It says 'returns flow data' but does not describe the structure or any limitations (e.g., time window, flow count). This is adequate but leaves gaps for an agent expecting a detailed response 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% coverage with a description for the 'mac' parameter, so the description adds little beyond the schema. The text 'by MAC address' reinforces what the schema already documents, making this baseline 3.

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 gets recent network flows for a specific device by MAC address. It uses a specific verb and resource, and distinguishes itself from sibling tools like get_top_talkers or search_flows by the device-specific 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 clearly implies the tool is for retrieving flows for a particular device via MAC address, giving it a clear context. However, it does not explicitly mention alternatives or when-not-to-use, so it lacks exclusions but still provides enough 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 only describes the output content but does not mention whether the data is real-time, how 'online status' is determined, or whether pagination or response limits apply.

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, front-loaded sentence with a parenthetical list of fields. Every word earns its place, and there is 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?

For a simple, zero-parameter tool without an output schema, the description is mostly complete. It states what is listed and the key fields. However, it could be improved by noting whether the list includes only the current network or all networks, or by giving a hint about the returned data 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?

There are zero parameters, so the baseline is 4. The description adds value by enumerating the returned fields (hostname, IP, MAC, manufacturer, online status), which is helpful even though parameter semantics are not applicable.

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 ('List all devices on the network') and identifies the resource ('devices') plus key output fields. The word 'all' distinguishes it from sibling tools like get_offline_devices, which targets a subset.

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?

No guidance is provided on when to use this tool versus alternatives. It does not mention that get_offline_devices or get_clients_by_network might be more appropriate for specific filtering needs, leaving the agent with no usage context.

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 of behavioral disclosure. It adds a useful behavioral trait — 'captures queries even for very brief connections' — which indicates the tool's comprehensiveness. However, it does not disclose return format, pagination, rate limits, or authentication requirements. This is a moderate level of transparency, but not exhaustive.

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 exceptionally concise: two sentences. The first sentence states the core purpose, and the second adds a comparative advantage and filtering capabilities. There is no redundant or extraneous information. Every word earns its place, making it highly efficient for an agent to parse.

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 moderate complexity (4 optional params, no output schema), the description is reasonably complete. It explains what the tool does, when it is more useful than alternatives, and what parameters it supports. The main gap is the lack of an explicit response shape, but since there is no output schema, the description could have mentioned the output format. Still, it provides enough context for an agent to select and invoke the tool effectively.

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% parameter description coverage, so the schema already documents all four parameters (mac, count, domain, hoursBack). The description adds some contextual meaning by mentioning 'filtering by device MAC, domain, and time range,' but this largely mirrors the schema. It does not introduce major new semantics beyond the schema, 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's function: 'Get DNS query logs showing every domain a device attempted to resolve.' It uses a specific verb ('Get') and resource ('DNS query logs'), and distinguishes itself from flow data by noting it 'captures queries even for very brief connections.' This makes it easy to differentiate from siblings like get_device_flows or search_flows.

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 usage context by explicitly comparing to 'flow data' and explaining why this tool is more complete for capturing DNS queries, even for brief connections. However, it does not name specific sibling tools or state when not to use this tool, so it falls short of full explicit when/when-not 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 full responsibility for behavioral disclosure. It implies a read-only 'List' operation but doesn't explicitly state that no state changes occur, nor does it clarify whether vulnerability scans are triggered or only existing results are returned. The description focuses on content scope but omits any operational behavior.

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 packs all relevant content into a compact list. Every element contributes to the purpose, with no filler or repetition. It is front-loaded with 'List' and immediately enumerates the distinct categories.

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 no parameters, no output schema, and no annotations, the description is reasonably complete for a listing tool. It covers the main data types returned, but could be enhanced by describing the response structure or including examples. However, the enumeration is sufficient for an agent to know what information is available.

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?

There are zero parameters, so the baseline is 4. The description adds no parameter information because none is needed; it's a list-all-style tool. This is appropriate for the tool's simplicity.

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 the specific verb 'List' and clearly identifies the resource: Firewalla features, global policy, per-network policy overrides, DoH status, and vulnerability scan status. This enumeration uniquely distinguishes it from sibling tools like get_system_info or get_network_status, providing a clear and specific purpose.

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?

No guidance is given on when to use this tool versus alternatives. It merely states what it lists without context on typical use cases, prerequisites, or exclusions. For example, it doesn't indicate whether this is the go-to for security status or if some data is available elsewhere.

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?

There are no annotations, so the description carries the full burden. It does not disclose behavior such as whether the operation is read-only, what the output format looks like, any rate limits, or any side effects. The phrase 'from the network monitor' adds minimal context, but the description is essentially a subject-verb-object statement with no behavioral depth.

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 that is front-loaded with the purpose and specific metrics. Every word contributes value, with no wasted text 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 tool with no parameters and no output schema, the description adequately lists the key metrics returned. It lacks details like time range or output format, but the tool's simplicity and the enumeration of metrics make it reasonably complete. Sibling context does not demand more.

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 tool has zero parameters, so the schema is fully covered and there is nothing to explain. Baseline for 0 params is 4, and the description adds no parameter semantics needed.

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 the specific verb 'Get' with a clear resource ('network performance metrics') and enumerates specific metrics (WAN latency, packet loss, DNS response times, connection quality). It distinguishes itself from some siblings (e.g., get_wan_usage) by listing these explicit metrics, though it does not explicitly name alternatives or differentiate from close siblings like get_network_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?

No guidance is provided on when to use this tool versus the many sibling tools. The description simply states what it does without mentioning context, alternatives, exclusions, or recommendations. This leaves the agent without clear direction on 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 carries the full burden of disclosing behavioral traits. It mentions the data categories returned, which hints at read-only behavior, but it does not explicitly confirm safety, explain data freshness, or note any side effects. For a 'get' tool this is minimally sufficient, but the description adds little beyond the obvious from the tool name.

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 efficiently lists the three main data types. It is front-loaded with the verb and resource, and every word contributes meaning. No fluff or 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 description is adequate for a simple read operation with no parameters or output schema, but it lacks clarity on how this tool differs from the many sibling tools. The listed data types (monthly bandwidth usage, speed tests, network monitor data) are somewhat vague and could overlap with get_wan_usage or get_network_performance. It does not specify the time range for 'recent' speed tests or the format of the returned data, leaving room for ambiguity.

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 tool has zero parameters, and the schema coverage is trivially 100%. The description does not need to explain parameters. The baseline for zero parameters is 4, and no additional param semantics are required.

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 gets network statistics, listing three concrete data types (monthly bandwidth usage, recent speed tests, network monitor data). This is a specific verb+resource, but it does not explicitly distinguish from sibling tools like get_wan_usage or get_network_performance, so it misses the top score.

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?

No guidance is provided on when to use this tool versus alternatives. The description simply states what it does, and the existence of many sibling tools with similar scope (e.g., get_wan_usage, get_network_status) is not acknowledged. There is no contextual 'when to use' or 'when not to use' information.

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. It discloses the tool's read-only nature as a health check and explicitly mentions the output (uptime, timestamp). While it does not elaborate on side effects or deeper behavior, the simplicity and clarity of the operation make this sufficiently transparent.

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 that efficiently states purpose and output. Every word contributes 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?

For a zero-parameter health check, the description fully covers what the tool does and what it returns. No output schema or annotations exist, and the simple scope means 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?

The tool has zero parameters, so schema coverage is effectively 100%. The description adds no parameter information, but none is needed, and the baseline for parameterless tools is 4.

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 identifies the tool as a health check for the Firewalla box, specifying that it returns uptime and timestamp. This distinguishes it from sibling tools like get_system_info or get_network_stats, which imply more detailed or different 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 explicit guidance on when to use this tool versus alternatives. It does not mention alternative tools or conditions under which to prefer this over get_system_info or get_network_performance, leaving the agent to infer usage from the name alone.

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 discloses useful behavioral traits: results are sorted by most recently seen and filtered by the configured hoursBack window. However, it does not mention whether the operation is read-only (though 'List' implies safe) or any error/edge-case behavior, leaving some room for improvement.

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 every word adds value. No wasted text or repetition of schema basics beyond necessary paraphrase.

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 one-parameter list tool with no output schema, the description covers the essential behavior: listing offline devices, sorting, and filtering. It lacks explicit mention of return format, but that is not strictly required. It is concise yet sufficient for correct invocation.

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 the hoursBack parameter with default and max values (100% coverage). The description repeats the filtering concept but adds no extra meaning or usage details beyond what the schema provides, so 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 uses a specific verb and resource ('List devices that have gone offline recently') and clearly differentiates from siblings like get_devices by specifying the offline condition and sort order. It is unambiguous and scoped.

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 this tool (when you need offline devices) but does not explicitly mention alternatives or exclusions. It does not state 'use get_devices for all devices' or provide any when-not guidance, so it only meets the implicit usage level.

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 transparency burden. It discloses that only active rules are shown by default (though the disabled param exists), includes hit counts, and supports filtering. It does not mention auth, rate limits, or return structure, but for a read-only list tool, it provides adequate 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?

Two concise sentences. The first sentence immediately states the primary function, and the second adds valuable details about rule types and filtering. 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?

Description covers the main output (rules with hit counts), rule types, targets, and filtering. It does not mention the disabled parameter or return formatting, but with no output schema and only three optional params, it is reasonably complete for assessing what the tool does.

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% for the three parameters. The description adds context about filtering by type and target, but does not elaborate on the 'disabled' parameter, which is already described in the schema. Baseline 3 is appropriate since the schema handles most parameter 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 clearly states the tool lists firewall rules/policies and includes specific rule types (block, allow, route) and targets (devices, groups, networks, domains, ports). This distinguishes it from sibling tools like get_alarms or get_devices by focusing on firewall rules.

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 this is the tool for listing firewall rules and mentions filtering by type and target, giving clear context for use. It does not explicitly state when not to use it or name alternatives, but the context is sufficient.

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 must convey safety and behavior directly. It clearly indicates a read-only operation via 'Get' and lists the returned information, but it does not disclose potential limitations (e.g., permissions, network dependency, or caching). For a simple info retrieval, this is adequate but not deeply transparent.

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 resource, then uses a colon to list the specific information included. It contains no fluff or redundant detail.

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 no output schema and a zero-parameter schema, the description bears the responsibility of explaining what the tool returns. It enumerates the key system attributes (firmware, model, branch, uptime, public IP, CPU/memory, hardware), providing sufficient context for an agent to understand the tool's purpose and result. The tool is simple enough that this level of detail is 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?

The tool has zero parameters, and the schema is empty, so there is nothing to explain. The description adds value by specifying the output fields, which is the relevant semantic context. The baseline for zero parameters is 4, and the description meets 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 explicitly states 'Get Firewalla system information' and enumerates specific fields (firmware, model, branch, uptime, public IP, CPU/memory, hardware), making it clear that this tool retrieves device-level system metrics. This distinguishes it from sibling tools focused on network data like devices, flows, or statistics.

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 by the word 'Get' and the resource 'system information', but it does not explicitly contrast with alternatives or state exclusions. The scope is self-evident—use when you need Firewalla system details—so usage is implied rather than clearly prescribed.

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 transparency burden. It explicitly states the tool 'Get's and 'Shows' target lists and their contents, implying a safe read-only operation. It adds useful context about the data returned, though it does not delve into permissions or output 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?

The description is two sentences, front-loaded with the primary action ('Get all target lists') and followed by a concise explanation of the content. 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 zero-parameter getter without an output schema, the description adequately explains what the tool returns (domain lists, IP lists, rules) and the scope (configured on the Firewalla). It could be more explicit about the exact response structure, but it is sufficient for a basic list retrieval 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 tool has zero parameters, and the schema is empty. The description adds context about what target lists are, but parameter semantics is trivially satisfied; baseline 4 is appropriate due to the 0-param rule.

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 gets all target lists, with the clarification that these are block/allow lists. It also specifies the content (custom domain lists, IP lists, associated rules), which distinguishes it from sibling tools that focus on devices, alarms, or network stats.

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 on when to use this tool: when the agent needs to see configured target lists. It does not explicitly name alternatives, but the tool's unique purpose is evident from the description and sibling context, making exclusions unnecessary.

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 burden of behavioral disclosure. It adds useful context by stating that output includes download, upload, and total bytes per device over a recent period. However, it does not explicitly state that this is a read-only query, nor does it disclose sorting behavior or how the 'direction' parameter affects results.

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 action and purpose, and contains no fluff. Every word contributes either to what the tool does or what it returns.

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 two optional parameters and no output schema, the description provides a reasonable overview of the return structure (bytes per device) and time window ('recent period'). However, 'recent period' is ambiguous, and the description does not clarify that 'count' limits the number of results, though this is covered in the 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 description coverage is 100%: both 'count' and 'direction' are described in the input schema. The description adds no additional parameter semantics beyond what the schema already provides, so it meets the baseline for high schema coverage without exceeding 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 uses a specific verb 'Get' and a clear resource ('devices ranked by bandwidth usage'), and introduces the 'top talkers' concept. It distinguishes itself from siblings like get_wan_usage (WAN-level) and get_network_stats (aggregate), though it does not explicitly name an alternative for comparison.

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 intended use case is implied by the description ('Get devices ranked by bandwidth usage'), but there is no explicit guidance on when to prefer this tool over siblings like get_device_flows or get_network_stats. No alternatives, exclusions, or prerequisites are provided.

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 transparency burden. It indicates a read-only operation by using 'List' and describes the data returned, but it does not explicitly state that the operation has no side effects, requires no special permissions, or mention any edge cases. This is adequate but not fully transparent.

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 concise sentences with no fluff. It front-loads the primary purpose and then lists the useful output attributes, earning every word.

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?

This is a simple zero-parameter list tool with no output schema. The description covers the main categories (network segments, VLANs, network groups) and the returned attributes (names, subnets, VLAN IDs, interfaces). It does not discuss formatting, ordering, or hidden items, but for this simple read-only use case 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?

The tool accepts zero parameters, and the input schema is empty. There are no parameter semantics to document; the baseline of 4 applies. The description adds value by detailing the output contents, which is the relevant semantic information for this tool.

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 the specific verb 'List' and clearly identifies the resource: network segments, VLANs, and network groups configured on the Firewalla. It also enumerates the returned fields (network names, subnets, VLAN IDs, interfaces), making its purpose unmistakable and distinct from sibling tools like get_devices or get_network_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?

Usage is implied from the description: call this tool when you need to retrieve the Firewalla's VLAN/segment configuration. It does not explicitly state when not to use it or mention alternatives, but given the focused resource and zero parameters, the intended use is reasonably 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 must disclose side effects, permissions, or read-only guarantees. It only lists output contents (profiles, clients, health) without addressing whether the operation is safe, requires auth, or has rate limits. The 'get' prefix suggests read-only but is not explicit.

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 primary action. 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?

With no params and no output schema, the description adequately covers the tool's purpose and output scope. It lists the key categories of information returned, which is sufficient for an agent to select and invoke the tool, though more detail on response format could be beneficial.

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 tool has no parameters, so baseline is 4 per rubric. The description does not need to explain parameters and instead clarifies what status information is included, adding 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?

States the exact function 'Get VPN status' and lists supported VPN technologies (WireGuard, OpenVPN, VPN mesh). This clearly differentiates it from sibling tools like get_network_status, which target generic network status rather than VPN-specific details.

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?

No explicit guidance on when to use this tool versus alternatives. However, the description implies it's the tool for VPN-related status, and no sibling tool directly covers VPN, so usage context is clear but not formally stated.

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 clearly indicates a read operation ('Get', 'Shows'), but it does not disclose whether data is real-time or historical, aggregation details, or potential access limitations. The behavior is transparent in intent but lacks depth expected without 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 two concise sentences that front-load the core purpose ('Get per-WAN data usage breakdown') and then provide a defining detail. There is 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?

The tool is simple with no parameters and no output schema. The description covers the essential return content (per-interface breakdown with download/upload totals), but could optionally specify units or time period. Overall, it is complete enough for a read-only tool of this simplicity.

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?

There are zero parameters, so the baseline is 4 per the rubric. The description adds no parameter-specific meaning, but none is needed since the schema is empty. It focuses on the output, which is appropriate for a parameterless tool.

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 a specific verb ('Get') and resource ('per-WAN data usage breakdown'), with explicit detail on what it shows ('bandwidth consumption per WAN interface with download/upload totals'). This clearly distinguishes it from sibling tools like get_network_stats or get_vpn_status, which focus on different scopes.

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 WAN-level data usage is needed, but it does not explicitly state when to use it over alternatives or provide exclusions. Sibling tools like get_network_performance could overlap, yet no guidance 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?

No annotations are provided, so the description carries the burden. It discloses what the tool returns and that filtering is supported, but it omits details such as default time range, max results, or any side effects/requirements (e.g., read-only behavior). The schema supplies some defaults, but the description itself adds limited behavioral context beyond the return fields.

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 concise sentences with the main action front-loaded in the first sentence and return details in the second. No redundant information 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?

The description covers the core purpose, filter capabilities, and return fields. For a 7-parameter tool with a complete schema, this is largely sufficient. However, it lacks guidance on when to use this versus related flow tools, and it does not clarify default behavior like time range or limit handling, which may be important for agents.

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 for all 7 parameters, so the description's filter list adds minimal value. The description mentions filters like device MAC, domain, IP, port, category, and time range, which directly correspond to parameters, but it does not provide any additional syntax, formatting, or edge-case guidance beyond the schema's 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 identifies the action (Search), the resource (individual network flow records), and provides specific return fields (destination IP, domain, port, protocol, bytes, country, app category). The term 'individual' and 'per-connection' helps distinguish from aggregate tools like get_top_talkers.

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 searching flows with filters, but it offers no explicit guidance on when to choose this over related tools like get_device_flows or get_top_talkers. There are no alternative suggestions or exclusion criteria.

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