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

The description extensively covers behavioral traits beyond annotations: automatic range splitting with dedup, definition of 'dimension' (including metadata keys), handling of optional parameters, output format (window, group_by, rows, truncated, total_count), sorting, and error responses. Annotations already declare readOnlyHint and openWorldHint, and the description adds significant context.

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?

Well-structured with a summary sentence, bullet inputs, and output format. Slightly verbose but each section adds value. Could be tightened slightly but overall 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?

Given no output schema and complex nested parameters, the description fully covers inputs, output shape (with optional fields), sorting, and error case. It leaves no major gaps for an agent to understand the tool's behavior.

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 only 50%, but the description provides detailed semantics for all parameters: ISO date format with inclusive end, optional group_by falling back to server config, filter_values max 200, filters with examples, and event_names. It also explains the dimension concept comprehensively.

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 aggregates event counts over a date range with optional grouping, explicitly calling it 'the workhorse for cohort comparison,' which distinguishes it from sibling tools like vexo_event_timeline or vexo_get_recent_events.

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?

Strong usage context is provided: designed for cohort comparison, automatic splitting of ranges >31 days. However, it does not explicitly state when not to use this tool or compare to alternatives, so it falls short of a 5.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds valuable behavioral details: UTC bucketing, auto-split for ranges over 31 days, meaning of gaps (no events), and error response format. These go beyond annotations and clarify important aspects not visible in the schema.

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

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

The description is well-structured with a clear purpose sentence, followed by use case, parameter list, and return output. It is concise but thorough, with each sentence adding value. A minor redundancy exists (event_names requirement stated twice) but does not detract.

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 having no output schema, the description provides a detailed return structure including fields like window, granularity, group_by, rows, truncated, and total_count. It explains sorting and gap semantics. Missing precision on optional total_count and truncation behavior, but overall complete for a tool of moderate 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?

With only 14% schema description coverage, the description compensates by explaining each parameter's semantics: event_names as required list with example, start/end_date as ISO dates (end inclusive), group_by defaulting to server key, filter_values with max 200, and granularity limited to 'day'. This adds significant meaning beyond the bare 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 clearly states it provides a per-day timeline of specific events for detecting cutover dates. It distinguishes itself from siblings like vexo_count_events (which counts events without bucketing) and vexo_get_recent_events (which returns raw events) by emphasizing the day-level aggregation and cutover detection use case.

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 recommends using this tool for cutover detection and notes that event_names is required. While it does not mention alternatives or when not to use it, the specificity of the use case and required parameters provide strong guidance. A slight improvement would be to contrast with sibling tools explicitly.

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?

Adds significant context beyond annotations: explains what events are scanned (ALL in date range), output limit (top 50 by frequency), derivation of event_name, date range constraints (max 31 days), inclusive end behavior, and failure case. No contradiction with readOnlyHint.

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?

Concise and well-structured: purpose sentence, usage hint, parameter explanations, return format, and error case. Every sentence adds value; 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?

Completely covers what an agent needs: purpose, when to use, parameter details with constraints, return structure, and failure mode. Despite no output schema, the description provides full return 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?

Schema coverage is 100%, but description adds format examples ('YYYY-MM-DD'), constraint (end <=31 days after start), and clarifies inclusive end for date-only inputs. Provides additional meaning beyond 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?

Description clearly states the tool's purpose: 'Discover the event-name vocabulary in a date window (schema discovery).' It distinguishes from siblings by focusing on name discovery (vs counting, timeline, recent events, sessions, overview).

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?

Explicit guidance: 'Use this FIRST when you don't know which event names exist.' This tells the agent when to invoke the tool versus alternatives.

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 provide readOnlyHint=true (read-only) and openWorldHint=true. The description adds important behavioral details beyond annotations: it scans a default 30-day lookback window, allows override via start_date/end_date, limits n to max 50, and describes the return format including truncated and total_count. No contradictions.

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 appropriately concise and well-structured: it starts with the core purpose, then provides usage context, a bulleted list of inputs with defaults, and a return format summary. Every sentence is informative and there is 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 4 parameters, nested objects, and no output schema, the description is complete. It covers purpose, when to use, parameter details with examples, return structure (including truncated and total_count), and failure case. An agent has all necessary information to select and invoke the tool correctly.

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 25% (only filters has a description). The description compensates fully: explains filters is a required key/value selector with examples, n is number of events (default 10, max 50), start_date/end_date are optional ISO dates. This adds substantial meaning beyond the schema, ensuring an agent can use parameters correctly.

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 purpose: 'Forensic dive into one entity's most recent raw events (newest first).' It uses a specific verb ('get') and resource ('recent events' for an entity). It also distinguishes from siblings by noting it is used after aggregate tools point to a specific entity, differentiating it from tools like vexo_count_events or vexo_overview.

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 guidance on when to use: 'Use after the aggregate tools point you at a specific entity and you need to read the actual event stream.' It implies not to use it for aggregated views. While it does not explicitly name sibling tools as alternatives, the context is sufficient for an AI agent to understand the appropriate scenario.

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 provide readOnlyHint=true and openWorldHint=true, and the description adds significant behavioral details: grouping by sessionId, returning N most recent per group, max limits, and the return structure including failure case. This adds substantial value beyond 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 well-structured with bullet points for inputs and return fields, making it easy to parse. While it is detailed, every sentence adds value, though it could be slightly more concise.

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 complexity (6 params, no output schema), the description fully covers inputs, return format, usage context, and failure handling. It is complete and provides all necessary information for an agent to invoke the tool correctly.

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 0%, but the description explicitly documents all six parameters with defaults, constraints, and examples (e.g., group_by defaults to server group key, n_sessions_per_group defaults to 20, max 50). This fully compensates for the missing schema 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 it summarizes recent app sessions grouped by an entity, distinguishing between 'bailed out' and 'event-poor' sessions. It uses specific verbs and differentiates from sibling tools like vexo_count_events and vexo_get_recent_events.

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 explains when to use it (to tell session types apart) and mentions default lookback window and optional date override. However, it does not explicitly list when not to use it or compare to alternatives.

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 scanning all events in date window (<=31 days), returning totals and top breakdowns, and the return shape including cap at 15 per top list and failure mode. Adds behavioral details beyond annotations (readOnlyHint, openWorldHint).

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 paragraphs with purposeful sentences. Front-loaded with purpose and usage. No fluff, every sentence 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?

Fully explains purpose, behavior, parameter constraints, return shape, and failure mode. No gaps given the tool's simplicity and lack of output 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?

Input schema parameters have 0% description coverage, but description explains they are ISO dates, end inclusive, and max 31 days apart. This adds essential semantic 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?

Clearly states 'High-level breakdown of activity in a date window' and 'Good first call to understand an app's traffic', specifying verb (overview) and resource (activity in date window). Distinguishes from siblings like vexo_count_events and vexo_event_timeline.

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 recommends as a first call for understanding traffic. Implicitly suggests when not to use (e.g., for detailed event counts or timelines, use other tools). No explicit exclusions, but context is clear.

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