plausible-analytics

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

The annotation readOnlyHint=true already establishes it as a safe read operation. The description adds the underlying API call (POST /api/v2/query with no dimensions), which is useful context, but it doesn't disclose additional behavioral aspects like rate limits or response format. Given the annotation coverage, a moderate score is appropriate.

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, front-loaded with the key purpose ('aggregate totals') and efficiently adds the API implementation detail. Every phrase earns its place 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 simple aggregate tool with strong schema coverage and a read-only annotation, the description is largely complete. It clearly defines the operation and contrasts with breakdown. However, since there is no output schema, the description doesn't specify the return shape (e.g., a single row of totals), which is a minor gap for agent expectations.

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% description coverage with detailed explanations for site_id, metrics, date_range, and filters. The description adds minimal parameter insight beyond the schema, only clarifying that there is no group-by dimension. Therefore, the schema carries the burden and a baseline of 3 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 clearly states 'aggregate totals for the given metrics over a date range (no group-by)' which specifies the verb, resource, and scope. It also differentiates from sibling tools like plausible_breakdown (which would involve group-by) and plausible_timeseries, making it uniquely identifiable.

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's a convenience tool for total aggregates without group-by. It doesn't explicitly name alternatives, but the 'no group-by' phrasing signals when to prefer this over breakdown or timeseries tools. No explicit exclusions are mentioned, hence a 4.

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

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

Annotations already declare readOnlyHint=true, so the safe-read behavior is known. The description adds value by revealing the underlying API call (POST /api/v2/query with dimensions=[property]) and the 'convenience' nature, but it does not disclose pagination, response structure, or other behavioral traits. This is adequate but not exceptional.

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 purpose, and includes a useful API mapping. Every word earns its place with no repetition of schema details.

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, combined with a rich schema and read-only annotation, gives enough context for an agent to invoke the tool correctly. It explains the core behavior and API equivalence, though it does not describe the return format or edge cases. For a convenience wrapper this is moderately 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 coverage is 100%, so the schema already documents all 7 parameters. The description reiterates the property examples already present in the schema and does not add new semantic meaning beyond pointing out the mapping to the API. 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 clearly states a specific action: "break metrics down by a single property (dimension)" with concrete examples like "visit:source or event:page". It distinguishes itself from sibling tools like timeseries (which breaks down by time) and aggregate (which does not break down).

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 by labeling itself as a convenience wrapper for the Plausible API and specifying the exact API call. It implies when to use it (when you need breakdown by a single property) but does not explicitly name alternatives or exclusion cases, so it misses the top score.

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

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

Annotations already declare readOnlyHint=true, covering the safety profile. The description adds a meaningful behavioral constraint: 'Requires an enterprise plan' (auth/permission). It also hints at the returned fields ('timezone, etc.'), though not exhaustively.

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 front-load the purpose ('Get a single site by its domain') and then provide the requirement and endpoint. No filler 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?

For a simple read-only tool with one parameter and no output schema, the description covers the purpose, identifier format, and permission requirement. It doesn't detail the full response structure, but 'timezone, etc.' gives a glimpse. This is adequate 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?

The input schema fully describes site_id as the domain, with an example. The description reinforces 'by its domain' but adds no new parameter semantics beyond that. Since schema coverage is 100%, 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 the specific verb 'Get' with the resource 'a single site' and the key 'by its domain', clearly distinguishing it from siblings like plausible_list_sites (which lists multiple). It also references the API endpoint, reinforcing precision.

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 gives clear context for when to use it (retrieving one site's details by domain) and notes the enterprise plan requirement. However, it doesn't explicitly name alternatives like plausible_list_sites or state when not to use it, so it lacks explicit 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?

The readOnlyHint annotation already signals a safe read operation. The description adds valuable context: the enterprise plan requirement and the exact API endpoint (GET /api/v1/sites/goals), which goes beyond the annotation's basic safety signal.

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 three short sentences that front-load the action, state an access constraint, and provide the endpoint. No wasted words; every piece adds value.

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

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

For a simple list tool with one parameter and a readOnly annotation, the description covers purpose, access, and endpoint. It doesn't specify the response shape, but the absence of an output schema and the straightforward nature of listing goals make this 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 input schema has 100% coverage for the single parameter site_id, including an example ('example.com'). The description itself doesn't add parameter details, so the baseline 3 is appropriate since the schema already does the heavy lifting.

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 'List the goals (conversions) configured for a site,' specifying the verb, resource, and scope. It distinguishes itself from siblings like plausible_breakdown or plausible_timeseries by targeting the 'goals' resource, and the endpoint reference adds specificity.

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 mentions 'Requires an enterprise plan,' which is a key prerequisite for using this tool, and the API endpoint implies when it applies. While it doesn't explicitly name alternatives, the purpose is clear enough for an agent to infer appropriate use.

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

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

Beyond the readOnlyHint annotation, the description adds behavioral context by mentioning the enterprise plan requirement and the cursor pagination approach. No contradictions with annotations; readOnlyHint aligns with a list operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the primary purpose, and includes the endpoint reference. Every sentence adds value with 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?

For a simple list tool with no output schema, the description provides adequate context: accessible sites, returned fields, pagination, and plan requirement. It lacks explicit error/edge-case info, but annotations and schema cover the basics well.

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

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

Schema coverage is 100%, with parameter descriptions for after, before, and limit. The description adds general pagination context but does not provide additional parameter-level semantics beyond what the schema already states.

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 identifies a specific action ('List'), a resource ('sites the API key can access'), and provides detail on what is returned ('domain + timezone'). It clearly distinguishes from sibling tools like get_site, which targets a single site.

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 explicitly states a key prerequisite ('Requires an enterprise plan') and mentions cursor pagination, giving clear context for when this tool is applicable. However, it does not explicitly mention alternatives or when not to use it, so it misses the explicit exclusion 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?

Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds no behavioral context such as response format, pagination behavior, or potential large result sets. It does not contradict the annotation but provides no additional disclosure.

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 short and front-loaded with the tool's identity. The endpoint reference 'POST /api/v2/query' is arguably redundant but not harmful, so it earns high marks for conciseness.

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 complex with eight parameters and nested objects, and there is no output schema to explain return values. The description provides only a one-sentence capability summary without usage context or expected response, leaving the agent to rely solely on 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?

All parameters have descriptions in the input schema, so the baseline is 3. The description's mention of 'optionally grouped by dimensions and narrowed by filters' is a high-level overview that adds little beyond the schema's explicit parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it computes metrics over a date range and supports grouping, filtering, ordering, and pagination. It identifies it as the 'full-power Stats API query', giving a clear sense of its role. However, it does not explicitly differentiate it from sibling tools like aggregate or timeseries.

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 siblings such as plausible_aggregate or plausible_timeseries. The phrase 'full-power' implies generality but does not specify exclusions or when a simpler tool would suffice.

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

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

Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds useful behavioral context: it clarifies the meaning of 'current' (active in the last 5 minutes) and specifies the return type as a single integer. It also provides the exact API endpoint, going beyond the annotation baseline without contradicting it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the core purpose in the first sentence. It contains exactly three short sentences: the function, the return type, and the API reference. Every sentence adds value without unnecessary fluff, making it exceptionally efficient.

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 tool with a single parameter and no output schema, the description fully covers what an agent needs: the metric definition, the parameter (via schema), the return type, and the endpoint. There is no missing information about pagination or complex behaviors. The combination of description, annotations, and schema 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 input schema has 100% coverage for the only parameter site_id, with a clear description including an example ('example.com'). The tool description does not add further parameter details, but since the schema already provides complete semantics, a baseline score of 3 is appropriate. No additional guidance is 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 clearly states the tool's function: 'Get the number of current visitors on a site (active in the last 5 minutes).' It specifies the resource (a site) and the exact metric (realtime visitor count), which distinguishes it from sibling analytics tools like plausible_timeseries or plausible_breakdown. The mention of the API endpoint further reinforces the 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 for when to use this tool: it's for current visitors active in the last 5 minutes, implying realtime rather than historical analysis. However, it does not explicitly name alternatives or state when not to use it, so it falls short of a 5. Still, the context is sufficient for an agent to differentiate it from the broader stats tools.

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?

The readOnlyHint annotation already discloses that this is a safe read operation. The description adds that it uses POST /api/v2/query with dimensions=[interval], which gives insight into the underlying API call, but it does not describe output format, pagination, or other behavioral traits. This is acceptable given annotations but not rich.

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 efficient sentences, front-loaded with the core purpose and backed by the API detail. Every word earns its place with 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?

For a tool with 5 params and no output schema, the description provides the essential core but lacks context on when to prefer it over siblings, what the returned rows look like, or any caveats like timezone handling. The rich schema and readOnlyHint mitigate this somewhat, making it minimally adequate but not 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 input schema has 100% description coverage, so parameters like interval, metrics, and date_range are already well documented. The description only mentions grouping by time interval, which adds no new meaning beyond what the schema's interval parameter already states. 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 clearly states this tool returns metrics over time grouped by an interval, distinguishing it from the sibling aggregate and breakdown tools. However, it lacks a strong verb like 'retrieve' or 'fetch', using 'Convenience' instead, which slightly weakens clarity.

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 such as plausible_aggregate or plausible_breakdown. The word 'Convenience' implies a wrapper, but there is no stated context, exclusions, or comparison with sibling tools.

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