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

No annotations are provided, so the description carries full burden. It does not disclose any behavioral traits such as whether the tool is read-only, authentication requirements, rate limits, or error behavior. The description only outlines the output, leaving the agent uninformed about side effects or constraints.

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, informative sentence that front-loads the key purpose and output components. It is concise with no wasted words. However, breaking it into bullet points could improve scannability, which prevents a score of 5.

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 no annotations, the description should compensate by detailing return values or behavioral nuances. It lists what is returned (stats, deltas, top lists) but lacks format, limits (e.g., always top 10?), or error handling. For a tool with 3 parameters, the description is incomplete for confident usage.

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 already describes all three parameters (range, country, website_id) with 100% coverage. The description adds minimal value by mentioning 'over a range', which loosely corresponds to the range parameter. It does not enrich parameter meanings beyond the schema, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool provides a 'one-call snapshot' with stats, deltas, and top lists for URLs, referrers, and events over a range. It distinguishes this consolidated report from sibling tools that focus on individual metrics (e.g., get_stats, get_event_data). However, it does not explicitly contrast with siblings, preventing a score of 5.

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 no guidance on when to use this tool versus alternatives like get_stats or get_event_data. It does not mention prerequisites, limitations, or scenarios where this tool is preferred. This omission makes it harder for an agent to select the correct tool.

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

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

No annotations provided, so description carries full burden. It mentions returning a clear note if the plan doesn't support the endpoint, but lacks details on read-only, destructive, or other behavioral traits.

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 purpose. No unnecessary 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?

Covers purpose, usage guidance, prerequisite, and alternative. No output schema, but return value could be hinted. Mostly complete for a moderately complex tool.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds minimal extra context beyond the schema (e.g., optionality of event_name). No significant enhancement.

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 custom event-data properties over a time window, optionally filtered by event name. It distinguishes from sibling get_metrics by mentioning that get_metrics is for simple event counts.

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

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

Explicitly states when to use (for event-data properties) and when not to (for simple counts, use get_metrics). Also mentions the prerequisite of an Umami plan that exposes event-data endpoints.

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?

Describes return format [{x, y}] but no side effects, auth needs, or limits. With no annotations, description should disclose more behavioral traits (e.g., what happens with empty results or invalid types).

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: one for purpose, one for format. No fluff, front-loaded with key action and examples.

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

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

Despite 7 parameters (4 required), description omits optional filter behavior, default limit, and edge cases. No output schema or annotations to compensate. Incomplete for autonomous agent reasoning.

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 covers 100% of parameters. Description adds context ('top values over a window') but doesn't elaborate beyond schema (e.g., meaning of limit, optional filters). Baseline 3 for high coverage with marginal added 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?

Description clearly states the tool returns top values for one dimension over a window, with examples. It distinguishes from siblings like get_stats (aggregate metrics) and get_pageviews (specific event).

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?

Implicitly suggests use for dimension breakdowns, but no explicit when-to-use vs alternatives (e.g., cohort_report, get_stats) or when-not-to-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?

No annotations are provided, so the description bears full burden. It describes the output (pageviews and sessions as a timeseries) but does not disclose side effects, authentication needs, rate limits, or behavior for large windows. It assumes read-only behavior, which is typical but 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?

The description is a single sentence of 12 words, efficiently conveying the core purpose without unnecessary detail. It is front-loaded with the key action and resource.

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 should hint at the return structure. It mentions 'pageviews and sessions' but does not specify the data format (e.g., array of objects with date and counts). It also lacks details on pagination or limits. For a tool with 6 parameters (3 required), this is 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?

Schema coverage is 100%, baseline 3. The description adds meaning by linking parameters to the overall purpose: 'window' explains start/end, 'bucketed by day or hour' explains the unit parameter, and 'pageviews and sessions' clarifies the metrics returned. This adds context beyond the schema's individual descriptions.

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

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

The description clearly states the tool retrieves 'pageviews and sessions as a timeseries over a window, bucketed by day or hour.' It specifies the resource (pageviews and sessions) and format (timeseries, bucketed), which distinguishes it from sibling tools like get_metrics or get_event_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 implies usage for time-series analysis over a window, but does not explicitly state when to use this tool versus alternatives like get_metrics or get_stats. No exclusion criteria or alternative tool references 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 full burden. It describes the output content (visitors, visits, etc.) and mentions previous period and deltas, but does not disclose side effects, read-only nature, rate limits, or authentication requirements. It 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 a single sentence that efficiently conveys the purpose and output fields with zero waste. It is front-loaded and earns its place.

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

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

Given no output schema, the description partially explains the return format by listing metrics, but does not specify types or exactly how previous period and deltas are structured. For a tool with 6 parameters, more completeness would be helpful.

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 baseline is 3. The description does not add meaning beyond the schema for parameters; it only mentions the window concept (start/end) implicitly. The schema itself already documents each parameter clearly.

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 that the tool returns summary stats (visitors, visits, pageviews, bounces, totaltime) for a website over a window, including previous period values and deltas. It is specific and distinguishes from sibling tools like list_websites or get_event_data, though not explicitly comparing to get_metrics or get_pageviews.

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

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

The description implies usage for obtaining high-level stats over a time window, but does not explicitly state when to use this tool versus siblings like get_metrics or cohort_report. No alternatives or exclusions are mentioned.

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 states the tool lists websites (read-only), but does not mention authentication requirements or rate limits. However, the behavior is transparent enough for a simple listing tool.

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

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

The description is a single sentence with no wasted words. It front-loads the core purpose and includes critical usage guidance.

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 no output schema, the description explains the return fields (id, name, domain). It provides clear context for use and distinguishes from siblings. All necessary information for an agent to invoke the tool 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?

Schema coverage is 100% with one parameter already described. The description adds value by mentioning the output fields (id, name, domain) which are not in the schema, helping the agent understand what the tool returns.

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

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

The description uses a specific verb ('list') and specifies the resource ('every website on the Umami account') along with the returned fields (id, name, domain). It also explicitly distinguishes itself from sibling tools by stating it should be called first to discover valid website_id values.

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 explicitly instructs when to use the tool: 'Call this first to discover valid website_id values for the other tools.' This provides clear context and prerequisite information.

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