Google Analytics (unofficial)

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

Annotations already indicate read-only and non-destructive. Description adds that the tool returns canonical graph, sources, metrics, dimensions, and live connectors, which is helpful but not extensive 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 sentences, front-loading the primary use case and adding a negative use case. Every sentence is meaningful with no waste.

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 only one optional parameter and no output schema, the description should cover the parameter. It does not explain the 'source' parameter, leaving a significant gap. The purpose is clear, but the missing parameter semantics make it incomplete.

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 has one parameter 'source' with no description or enum. Description does not mention the parameter at all, leaving its purpose entirely unclear. Schema description coverage is 0%, so the description fails to compensate.

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 discovers the marketing reporting graph, sources, metrics, dimensions, and live connectors. It distinguishes from GA4 discovery but doesn't fully differentiate from sibling 'marketing_get_sources' which may overlap.

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?

Tells when to use (for discovery of catalog) and when not to use (GA4 account discovery or data retrieval). Does not list alternative sibling tools by name, but implication 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?

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds context about the types of funnels and cross-source capabilities but does not disclose additional behavioral traits such as rate limits, quota handling, or data freshness. Given annotations, the description provides adequate but not extra behavioral 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?

The description is a single paragraph that is reasonably concise and front-loads the main purpose. It could benefit from bullet points or clearer structure, but it is not overly verbose and each 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?

Considering the tool's complexity (16 parameters, nested objects, no output schema), the description is insufficient. It gives a high-level overview but lacks guidance on how to structure the funnel parameter, use filters, or interpret results. An agent would need additional knowledge to correctly invoke the 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 low at 44%, and the tool description does not compensate. The description only mentions date ranges and funnel types; it does not explain key parameters like app, funnel, funnelBreakdown, or filter expressions. The schema provides some descriptions, but overall parameter semantics are insufficient for an agent to use the tool 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 it is for ordered conversion-step analysis and cross-source holistic_bundle landing-page funnels. It provides specific examples like session_start → add_to_cart → purchase and mentions covering drop-off, conversion paths, and acquisition-to-conversion context. This distinguishes it from sibling tools like marketing_get_report.

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 tells when to use the tool: for ordered conversion-step analysis and cross-source funnels. It also indicates using one or two date ranges for comparison. However, it does not explicitly state when not to use it or compare to alternative tools like marketing_get_report.

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 indicate read-only and open-world behavior. Description adds valuable context: merging of sources aligned on landing_page, passthrough of unknown GA4 names to API, limitations across sources (GA4 lacks query, Search Console lacks sessions), and defaults for sources. No contradiction with 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?

Description is long but front-loaded with key points. It is well-structured, covering purpose, usage, and technical details. However, it could be more concise; some sentences are dense and may require multiple reads. Earns its place but not optimally 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 tool's complexity (27 parameters, no output schema), the description covers many aspects: data sources, merging, dimension restrictions, period-over-period, passthrough. But it lacks output format details and does not explain all parameters. For a complex tool, this is moderately complete but has notable gaps.

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 low (37%), so description must compensate. It adds meaning for dateRanges (single vs dual for period-over-period), sources, and sourceMode. But many parameters (e.g., app, site, limit, offset) are not explained beyond their schema definitions. The description partially mitigates the gap but not fully.

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 it is the primary reporting tool for GA4 properties/sites, covering totals, trends, breakdowns, and period-over-period comparisons. It mentions specific metrics and dimensions. However, it does not explicitly differentiate from sibling tools like marketing_get_funnel or marketing_get_sources, though the context implies distinct purposes.

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?

Description implies it is the go-to report tool and suggests narrowing with sources or sourceMode='single' for specific queries. It notes per-source detail stays in sourceSections, hinting at when to use alternate sources. However, it does not explicitly state when to use siblings like get_funnel or get_sources, leaving some ambiguity.

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 and destructiveHint. The description adds valuable behavioral details about what's 'listed' (connected and missing sources, mappings), helping the agent understand the tool's output without a 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 informative and front-loaded with a comprehensive list. Each sentence adds value, though the list could be slightly more structured. 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?

Given no output schema and 2 parameters, the description adequately states the tool's purpose and when to use it. However, it lacks details on output format (JSON? array?) and does not fully describe parameter usage, leaving some gaps for the agent.

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%. The description mentions items matching the sources enum (GA4, Search Console, Bing) but does not explain the surfaceId parameter. Key parameter surfaceId is left undocumented, failing to compensate 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 uses a specific verb 'Lists' and enumerates many concrete resource types (GA4 properties, web streams, app streams, etc.), clearly differentiating from sibling tools like marketing_get_catalog or marketing_get_report.

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 'Use this before reporting when property/site selectors are unknown', providing clear context. While it doesn't say when not to use, the statement implies alternatives exist for known selectors.

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 indicate readOnlyHint=false and destructiveHint=false. The description adds behavioral context by naming the two actions (get vs update) and mentioning the specific selector types. However, it lacks detail on side effects (e.g., whether update overwrites or merges) and does not disclose any permission or limitation info beyond the 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 exceptionally concise: two short sentences. The first sentence states the general purpose, and the second gives specific usage instructions for the 'action' parameter. Every word adds value, 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?

Given the tool's complexity (6 parameters, nested objects, no output schema), the description is far from complete. It omits explanations for 'name', 'surfaceId', 'mainDomain', 'selectorSets', and the detailed structure of 'selectors'. While the core action is clear, the agent would lack context for correctly using most parameters.

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%, so the description must compensate. It only mentions the 'action' parameter and loosely lists the three selector types (ga4, search_console, bing_webmaster). Key parameters like 'name', 'surfaceId', 'mainDomain', and 'selectorSets' are completely unexplained. The nested structure of 'selectors' is also not described, offering minimal improvement over 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 the tool gets or updates persisted selectors for an analysis surface, specifying two distinct actions via the 'action' parameter. It lists the three supported selector types (GA4, Search Console, Bing Webmaster). However, it does not explicitly differentiate from sibling tools like marketing_get_catalog, but the resource focus is distinct enough.

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 each action: 'Use action='get' to inspect mappings and action='update' to persist... selectors.' This provides clear context for the two modes. No exclusions or alternative tools are mentioned, but the sibling tools likely serve different purposes (e.g., getting reports, catalogs), so the guidance is adequate.

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