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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'get detailed information,' which conveys read-only intent but does not disclose response shape, error behavior, permissions, or anything beyond the basic 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?

A single, front-loaded sentence with no filler. Every word contributes to identifying the tool's purpose and the required input's 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?

For a simple single-parameter read tool, the description is adequate: an agent knows what to call, what argument to pass, and where to obtain that argument. It could mention return details, but the tool's simplicity keeps this from being a major gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents id as 'Host ID,' and the description adds practical meaning by specifying that the ID is the one returned by unifi_list_hosts. This provenance helps an agent construct the call correctly and is not present in 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?

States a clear verb-resource pair: get detailed information about a single host. It explicitly distinguishes itself from unifi_list_hosts by scoping to one host by ID, so an agent can tell them apart immediately.

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 correct workflow: call this after unifi_list_hosts and pass the host ID returned there. It does not explicitly state when not to use it or name alternatives, but the intended 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?

With no annotations, the description carries the behavioral burden. It discloses account-wide scope, granularity options, and retention windows ('5-minute data is retained at least 24h; 1-hour data at least 30 days'). It does not mention output format or rate limits, but the main behavioral traits are 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?

Three sentences with no filler. The action and scope are front-loaded, followed by retention details and the parameter constraint, making the most decision-relevant information easy 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?

The description covers input constraints and retention but does not clarify the difference from unifi_query_isp_metrics, and there is no output schema to describe the return shape. For an agent choosing among similar ISP-metric tools, the missing sibling differentiation is a real gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents every parameter and its constraints. The description restates the mutual-exclusion rule but adds little new semantic meaning 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 states a specific action and resource: 'Get WAN/ISP health and traffic metrics for every site linked to this API key's account'. This is clear and scoped, though it does not explicitly differentiate from the sibling unifi_query_isp_metrics.

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 by defining its scope and retention behavior, but it gives no explicit guidance about when not to use it or how it compares to siblings like unifi_query_isp_metrics. The parameter rule about duration vs timestamps is helpful, but tool-selection guidance is missing.

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 for behavioral disclosure. It notes the data is 'admin-gated' and indicates network-topology data, but does not mention security implications, potential side effects, or rate limits. Since it's a read operation, that's expected, but the description adds little beyond what the name implies.

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, information-dense sentence that front-loads the main purpose and enumerates the key 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 read-only retrieval tool with one parameter and no output schema, the description is quite complete. It lists what the topology includes and notes the admin-gating. The only gap is not mentioning that the output format might have nesting, but that's minor given the low 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 schema already documents the id parameter. The description adds that the id is from unifi_list_sdwan_configs, which is useful context beyond the schema. This justifies a slightly above-baseline score.

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 the full topology for one SD-WAN configuration, enumerating specific contents (variant, settings, hubs/spokes, site/host IDs, network IDs, routed subnets). This distinguishes it from sibling tools like unifi_get_sdwan_config_status and unifi_list_sdwan_configs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies use for retrieving a specific configuration's topology, and the parameter description mentions id is as returned by unifi_list_sdwan_configs, which gives context. However, it does not explicitly state when not to use it or contrast with alternatives like unifi_get_sdwan_config_status.

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 adds useful context that the data is network-topology and admin-gated, and it lists the type of data returned. Still, it does not explicitly state that the operation is read-only, mention error behavior, or address rate limits or permissions beyond 'admin-gated'.

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 with no filler. The primary action is front-loaded, the output details are compactly listed, and the access restriction is appended in a short clause. Every word contributes to the agent's 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?

For a one-parameter tool with no output schema, the description covers the key return categories and the access requirement. It does not describe the exact status values or response format, and it omits an explicit read-only statement, but given the simplicity of the tool, the definition is nearly 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%: the single 'id' parameter is documented as 'SD-WAN config ID (as returned by unifi_list_sdwan_configs)', which already guides the agent on obtaining the value. The tool description adds no further parameter-level meaning beyond referencing 'one SD-WAN configuration', so it meets the baseline for full schema coverage without elevating 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-resource pair ('Get deployment status for one SD-WAN configuration') and enumerates exactly what the status includes (generation/apply status, per-hub/spoke details, WAN IPs, latency, routes, errors/warnings). This clearly distinguishes it from the sibling unifi_get_sdwan_config, which presumably returns the configuration itself rather than its deployment 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?

The description implies the tool is for status retrieval, and the schema notes the ID comes from unifi_list_sdwan_configs, suggesting a workflow. However, it does not explicitly state when to use this tool over alternatives like unifi_get_sdwan_config, nor does it mention any exclusions or conditions. Usage context is implied rather than 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?

No annotations are provided, so the description carries the full behavioral burden. It adds genuine value by flagging PII, admin-gated access, and the output fields (MAC, IP, model, firmware status, adoption/uptime), plus the 'grouped by host' behavior. It does not mention rate limits, response envelope, or default filtering, but for a list operation the key behavior and data-sensitivity are 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: the first states action and scope, the second summarizes output fields and adds a concise PII warning. No filler or redundancy; every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by enumerating the key returned device attributes and grouping behavior. It also conveys access-sensitivity, which matters for an admin-gated PII-bearing tool. Minor gaps like exact response pagination envelope are absent, but the schema covers pagination parameters and the description covers the essential context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters (time, hostIds, pageSize, nextToken). The description adds no parameter-level meaning beyond schema, which is consistent with the baseline 3 for a fully-covered 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 begins with a specific verb-resource pair ('List UniFi devices') and adds a precise scope ('managed by hosts this API key's account owns or super-admins') plus grouping behavior. This clearly distinguishes it from sibling tools like unifi_list_sites and unifi_list_hosts, which target different resources.

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 useful context about ownership scope and admin gating, which implicitly tells an agent this is the device-listing tool for host-owned UniFi devices. However, it never explicitly names alternatives or states when NOT to use it (e.g., versus unifi_get_host for a single device), leaving routing partially to inference.

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 disclosure burden. It openly positions the operation as a list/read action and lists the included data: hardware ID, IP address, ownership/block status, and timestamps. It does not mention pagination details or data freshness, but the existing schema already covers pagination parameters.

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 with no filler. The main action and scope are front-loaded in the first sentence, and the second sentence concisely lists the output categories. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list operation with two optional parameters and no required inputs, the description gives enough information for an agent to invoke it correctly. It clarifies scope and return content, though it could improve by explicitly addressing pagination behavior or contrasting with sibling list tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents pageSize and nextToken. The description adds no extra parameter-level meaning, but none is needed because the parameter descriptions are self-sufficient.

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 names a specific verb ('List'), a precise resource ('every host'), and clarifies what counts as a host ('UniFi console or network-server application'), which sets it apart from sibling tools like unifi_list_devices or unifi_list_sites. It also enumerates the returned fields, leaving no doubt about the tool's function.

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 this is for listing all hosts under the account, but it does not explicitly say when to prefer it over alternatives such as unifi_get_host or unifi_list_devices. There is no 'use this when...' or 'not for...' guidance, so an agent must infer the scope from the wording.

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 transparency burden. It does disclose the operation is read-only, tied to the API key's account, and only returns a subset of fields. It does not mention potential pagination, errors, or rate limits, but for a simple listing tool the core behavior is clearly 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?

The description is a single, focused sentence that front-loads the action and resource, then adds the scope and field limitation. Every word contributes useful information with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there is no output schema, the description adequately explains what will be returned (id, name, type only). It could mention pagination or point to get_sdwan_config for full data, but for a simple parameterless list operation the essential context is present.

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 0 parameters and the schema coverage is 100%, so there are no parameter semantics to clarify. The zero-parameter baseline of 4 applies; the description further clarifies the expected response fields, adding value 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') with a clear resource ('SD-WAN configurations'), explicitly scopes it to the account's configurations, and specifies the returned fields ('id, name, type only'). This makes it easy to distinguish from sibling get_sdwan_config or list_devices tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'List every' clearly conveys enumeration over all configurations, which implies use cases for browsing or overview rather than retrieving a specific config. However, it does not explicitly mention the sibling get_sdwan_config as the alternative when full details are needed, so guidance is adequate but not fully explicit.

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 does add meaningful context: results are scoped to the API key's UI.com account and include the caller's permission level, which signals authorization-dependent output. However, it does not explicitly state that this is a read-only operation, nor does it mention pagination behavior or any other edge cases.

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 front-loads the action and scope, then lists the returned content fields. Every clause adds information; there is no filler or redundant wording.

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?

Since there is no output schema, the description helpfully outlines what each returned entry contains (IDs, metadata, stats, permission level). It also clarifies the source (hosts running the UniFi Network application) and the account-scoping. The only missing context is pagination behavior and edge cases, which are minor for a straightforward list operation.

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 covers 100% of the parameters (pageSize and nextToken), each with its own description, so the baseline is 3. The tool description adds no parameter-specific guidance, but the schema already carries that weight, so no deduction is warranted.

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 begins with a specific verb and resource: 'List every UniFi site', further scoped by 'visible to this API key's UI.com account'. It enumerates exactly what each entry includes (IDs, metadata, stats, permission level), leaving no ambiguity about the tool's function. This clearly distinguishes it from sibling tools that list hosts, devices, or SDWAN configs.

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: if you need UniFi sites visible to the account, or site IDs/metadata/stats, this is the tool. However, it never explicitly names alternatives like unifi_list_hosts or unifi_list_devices, nor does it state when not to use this tool. The guidance is inferred from the resource name rather than 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 provided, the description carries the full behavioral burden and handles it well: it discloses that the operation is 'a filtered read, not a mutation, despite being a POST' and details the partialSuccess/outright-failure auth semantics. This preempts two likely agent misjudgments — assuming POST implies a write and assuming failures are uniform.

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 zero filler: the core purpose is front-loaded first, followed by the POST-method caveat, then the failure semantics. Every clause earns its place and nothing repeats what the schema already states.

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 2-parameter tool with a complete schema and no output schema, the description covers purpose, interface-safety context, and error behavior. The remaining gaps are minor: typical response contents and default behavior when beginTimestamp/endTimestamp are omitted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the interval enum and host/site pairs with optional time ranges are already documented in the schema. The description's 'host/site pairs and time ranges' phrasing reinforces the parameters but does not materially extend their meaning, placing it at the baseline 3 for fully-covered schemas.

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 and resource: 'Get WAN/ISP health and traffic metrics' scoped to 'specific host/site pairs and time ranges.' This clearly identifies what the tool does, but it does not explicitly distinguish itself from the near-twin sibling unifi_get_isp_metrics, so it falls just short of full sibling differentiation.

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 scoping phrase 'for specific host/site pairs and time ranges' implies the usage context, and calling it a 'filtered read' hints at selection logic. However, no alternative tools are named and no explicit when-to-use versus when-not-to-use guidance is provided, so the agent must infer the routing decision among siblings.

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