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

Annotations already cover read-only, idempotent, open-world, non-destructive. The description adds genuinely new operational context: it requires the Google Analytics Admin API to be enabled but needs no extra OAuth scope, and it documents the response shape and configured_property_id. Missing only rate-limit/pagination-limit behavior.

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 dense but well-ordered paragraph: capability, then handoff to siblings, then return shape, then prerequisites. Front-loaded and largely waste-free, though packed tightly.

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 usefully enumerates return fields and the configured_property_id, plus the API prerequisite. It stops short of explaining the pagination/truncation ceiling implied by max_pages or what 'configured' means 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 100% and max_pages is fully documented in the schema (pages of 200 accounts, max 20). The description adds nothing about the parameter, so baseline 3 is correct.

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 specific verb+resource (read GA4 accounts/properties via Admin API accountSummaries) and even names the exact data source. It distinguishes itself from siblings by explaining it produces the property_id that ga4_report and ga4_realtime consume.

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 says when to use it and what to do with the result ('find a property id itself and pass it as property_id to ga4_report or ga4_realtime'), naming the two sibling tools. The dispatching intent is unambiguous.

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 readOnly/idempotent/non-destructive, so the bar is lower. The description adds a real behavioral constraint beyond them — data is limited to the last 30 minutes — plus the return shape, though it says nothing about rate limits, realtime API quotas, or sampling.

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 short, front-loaded sentences: what it is, when it is useful, what it returns. No filler, and the scope constraint (30 minutes) comes before anything else.

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 inline return shape ('rows', 'row_count', 'totals', 'metrics') usefully fills that gap, and all three parameters are documented. Only minor omissions remain, such as the realtime API's data freshness or result limits.

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%, with each parameter (metrics, dimensions, property_id defaulting to GA4_PROPERTY_ID) fully documented in the schema. The description adds nothing about parameter syntax or valid values, so the baseline 3 applies.

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 specific verb+resource+scope: 'GA4 realtime report for the last 30 minutes'. An agent immediately knows this is the realtime variant versus a historical report, though the sibling ga4_report is never named for direct contrast.

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?

'Useful to check a tracking change, for example that one page view is counted once and not twice' gives a concrete when-to-use scenario. It lacks any when-not-to-use guidance (e.g. use ga4_report for historical windows), so it stops short of 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 readOnly, idempotent, non-destructive and open-world, yet the description adds substantial context beyond them: the returned shape (rows, totals, row_count, truncated), the fact that totals cover every row regardless of limit, metric unit/definition metadata, currency, and a date_range resolved to calendar dates in the property's timezone with data_complete. This is exactly the behavioral disclosure structured fields cannot carry.

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?

Purpose and scope come first, followed by the return contract and the sibling pointer — front-loaded and information-dense with no filler. The return-shape clause packs several quoted keys into one sentence, which reads slightly clunky but is justified given there is no output schema.

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 must describe the response, and it does so thoroughly (rows, totals, row_count, truncated, metrics, currency, resolved date_range). For a 7-parameter read tool with full schema coverage and complete annotations, nothing an agent needs to call it correctly is missing.

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 limit, metrics, dimensions, dates, property_id and channel_group, including defaults and the 1-1000 bound. The description adds no syntax or format detail beyond that, so the baseline 3 applies.

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 specific verb and resource ('Run a Google Analytics 4 report (Data API runReport)') and names the scope: traffic, conversions or revenue split by dimensions over a date range. It also explicitly contrasts with the ga4_realtime sibling, so an agent can tell the two apart without opening schemas.

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 routes the agent to ga4_realtime for the last 30 minutes, which is a clear when-to-use-this-vs-alternative statement. It lacks broader eligibility context (e.g. where metrics/dimensions account for unavailable combinations), so it falls short of a full 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, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds a concrete behavioral constraint the annotations do not: a hard quota of 2,000 inspections per day, which materially affects how an agent should batch calls. It omits any note on error behavior for URLs outside the property.

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 purpose and then the returned fields, ending with the quota constraint. No filler or restatement of the tool name.

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 usefully enumerates what the response contains, which is exactly the missing structured information. For a one-parameter, read-only inspection tool this is nearly sufficient; only error/edge-case behavior is unaddressed.

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?

There is a single parameter with 100% schema description coverage, so the schema already explains that the URL must belong to the configured Search Console property. The description adds no syntax, format, or constraint detail beyond that, which is the expected baseline when the schema 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?

States a specific resource and action: returns Google index status for a single URL via the URL Inspection API, enumerating the returned fields (verdict, coverage state, canonicals, robots.txt, fetch state, last crawl). An agent can tell this is a per-URL diagnostic read. It does not explicitly differentiate itself from the sibling indexing_status, so it stops short of a 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?

Usage is implied by the name and the 'one URL' scoping, and the quota line hints that it is a metered, limited operation. However, there is no statement of when to prefer this over indexing_status or gsc_performance, and no prerequisites or exclusions are given.

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 cover read-only/idempotent safety, but the description adds genuinely useful behavior: top-rows truncation with a "truncated" flag, "totals" computed over the whole period regardless of the requested split, Pacific Time date range, and a "data_complete" indicator. It stops short of describing rate limits or pagination mechanics.

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, fully front-loaded: metrics first, then returned structure. No filler wording, and the key behavioral caveats (totals, truncated, timezone) are packed into the second sentence efficiently.

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 well by enumerating the response keys (rows, totals, truncated, metrics, date_range, data_complete). A read-only tool with full annotation coverage needs little more; only finer details like sort order or error conditions are absent.

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 carries parameter meaning and a 3 is the baseline. The description restates the split dimensions (query, page, country, device, date) and notes that totals ignore the split, but omits searchAppearance and adds no format detail 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 names a specific resource (Search Console search performance for the configured property) and enumerates the exact metrics (clicks, impressions, CTR, average position) and split dimensions. It is clear what the tool does, though it never explicitly positions itself against siblings like ga4_report or gsc_inspect_url.

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?

There is no guidance on when to use this tool versus alternatives such as ga4_report or gsc_inspect_url. Defaults for date range are implied only indirectly via the schema, not the description, so the agent must infer usage context.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by disclosing what the payload contains (submission/download timestamps, errors, warnings), which goes 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?

A single front-loaded sentence that names the resource and its payload with zero filler. Nothing to trim.

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 no-parameter read tool with no output schema, the description gives a reasonable picture of the return fields, which is what an agent needs. It could be slightly more complete by noting scope (per-property) or how to use the results, but it is 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 tool takes zero parameters, so there are no parameter semantics to document and the baseline of 4 applies. The schema is trivially complete with 100% coverage.

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 the specific resource (sitemaps declared in Search Console) and enumerates the returned fields (last submission, last download, errors, warnings). It is clear what the tool retrieves, though it doesn't explicitly name a verb like 'list' or differentiate itself from siblings such as gsc_performance.

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?

There is no guidance on when to use this tool versus alternatives like gsc_performance or gsc_inspect_url. No prerequisites, no context about when sitemap data is relevant, and no exclusions are given.

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 readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds real behavioral context beyond that: it reads only the default workspace, translates built-in trigger ids (e.g. All Pages), and includes the published version id. It does not mention response size or paging, which is the only notable gap.

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 what the tool returns and no filler. The second sentence is a small add-on hint rather than noise, though the first sentence is slightly dense with parenthetical field lists.

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 does the work of describing the returned data (tags/triggers/variables fields, published version id, translated trigger ids), which is adequate for a zero-argument read tool. It stops short of covering response size, workspace selection assumptions, or error conditions.

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 takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies.

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?

Names the exact resource and scope: tags (with type, paused state, firing triggers, parameters), triggers, variables of the container's default workspace, plus the live published version id. That is specific enough to distinguish it from the GA4/GSC/Merchant siblings, which cover entirely 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?

"Useful to spot a tag configured twice" implies a use case (auditing/duplicate detection) but gives no explicit when-to-use conditions, prerequisites, or alternatives. Usage is inferable 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?

Annotations already declare readOnly=true, idempotent=true, openWorld=true, so 'nothing is submitted' mostly restates them. However, the description adds genuinely new behavioral context: it reveals the notification-type vocabulary (URL_UPDATED / URL_DELETED) and, importantly, that most URLs were never notified and this is reported as such – preventing an agent from misreading an empty response as an error.

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 tight sentences with the core purpose front-loaded and no filler. Slightly terse given there is no output schema, but 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?

For a single-parameter read tool with no output schema, the description covers the relevant scope: what is returned (notification records), the notification types, and the common empty case. It lacks detail on the returned record shape because no output schema exists, but it is sufficient to call 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 100% with a single 'url' parameter that the schema already documents as 'Full URL to look up'. The description adds no format, canonicalization, or property-vs-URL semantics beyond the schema, so baseline 3 applies.

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 specific verb+resource: retrieves the latest Indexing API notifications (URL_UPDATED / URL_DELETED) Google holds for a URL. This is clearer than a generic status check, but it never distinguishes itself from the closely related gsc_inspect_url sibling, leaving the agent to infer which indexing-status tool to pick.

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 ('Latest ... notifications ... for a URL') and gives a useful empty-result expectation, but never states when to use this versus gsc_inspect_url or other URL-level siblings, nor any prerequisites. Usage is implied rather than guided.

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 fully declare the behavioral profile (readOnly, idempotent, non-destructive, open-world), so the description owes little here. What it does add is only a content list; it says nothing about auth requirements, pagination, or how sources are keyed, so it contributes almost no behavioral context beyond the structured hints.

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?

One short noun-phrase line, front-loaded with the resource name and followed by the content categories. Nothing is redundant, though the fragment style means the action itself is left implicit.

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 zero-parameter read tool with no output schema, the description gives a reasonable hint at the returned fields but never states the shape of the result (list vs. single object, grouping, sorting) or scope limits. It is adequate but leaves the agent guessing about the response.

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 takes zero parameters, which sets the baseline at 4. The description's field list (labels, countries, languages, fetch URLs) is essentially descriptive metadata about the payload rather than a parameter explanation, so there is no gap to compensate for.

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 resource (Merchant Center data sources/feeds) and enumerates the content it covers (labels, countries, languages, fetch URLs), so an agent knows the domain. However, it supplies no verb at all — it never says whether the tool lists, fetches, or summarizes these sources — and it draws no boundary against the sibling merchant_report_query.

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?

There is no when-to-use guidance, no prerequisites, and no mention of the adjacent merchant_* siblings (merchant_product_issues, merchant_report_query) that an agent must choose between. The agent is left to infer the trigger condition entirely.

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 establish readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds real behavioral context beyond that: it scans every page of products up to max_pages and reports a truncation flag, which tells the agent how to interpret partial results. It stops short of 5 by not mentioning auth requirements or rate-limit/scan-cost implications of paging up to 200 pages.

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 densely packed sentences with the core purpose front-loaded; the inline return-shape sketch is justified because there is no output schema. Slightly long, but almost every clause carries information about either scope or output structure.

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 usefully closes that gap by specifying the returned keys (products, offer_id, issues, scanned, truncated). It covers paging and truncation semantics but says nothing about authentication, quota, or what destinations/labels mean, leaving minor gaps for a multi-parameter read 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 the baseline is 3. The description goes slightly beyond the schema by tying max_pages to the scan behavior and the returned truncated flag, clarifying why the agent should care about that parameter rather than just its range.

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 resource and scope: Merchant Center products with item-level issues (disapprovals, demotions, warnings) per destination, plus the attribute to fix. This is far more specific than the sibling names merchant_report_query or merchant_data_sources, but it never explicitly contrasts itself with those siblings, so it stops short of a 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?

Usage is implied by the framing (this is the tool you call to audit product-level issues), and the only_with_issues default of true hints at the default audit workflow. There is no explicit when-to-use/when-not-to-use statement and no mention of when a sibling such as merchant_report_query would be preferable.

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, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine value beyond them by disclosing that it hits Merchant API reports:search and that it returns Google's raw result rows rather than a normalized/transformed shape.

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 short sentences, front-loaded with the action and the API surface, followed by the return shape. No filler; slightly more compact than most peers.

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 correctly compensates by noting the return is Google's raw result rows, and the single input parameter is fully specified in the schema. An agent has enough to call it correctly, though pagination/result-size behavior is unstated.

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% and the single parameter is fully documented in the schema (MCQL statement, available tables, product_view id requirement, performance metrics). The description only restates "with an MCQL query" and adds no syntax, default, or format detail beyond the schema, so the baseline 3 applies.

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 specific verb and resource ("Run a Merchant Center report") and names the underlying API call (reports:search) plus concrete use cases (product status, free-listing performance). It is distinguishable from the GA4/GSC siblings, though it does not explicitly separate itself from merchant_product_issues, which covers overlapping product-status territory.

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 it by giving two example report categories, which is useful context, but it offers no exclusions or alternatives — it never says when to reach for merchant_product_issues or merchant_data_sources instead. Usage is inferable but not 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?

Annotations already declare readOnly, idempotent, non-destructive, and open-world, so the safety profile is covered. The description meaningfully adds that scores are bounded 0-100, that CrUX data only appears when real-user data exists, and that the anonymous shared quota can be bypassed with PAGESPEED_API_KEY — real behavioral/rate-limit context beyond the structured fields.

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?

Roughly two sentences, front-loaded with the output payload and ending with the quota/auth caveat. No filler or repetition; each clause carries information. Dense metric enumeration is justified for a scoring tool.

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 correctly carries the burden of describing return values (scores, LCP/CLS/TBT, CrUX category) and the auth/quota caveat. The one shortfall is silence on the strategy parameter's effect on the returned scores, but otherwise it is complete for a two-parameter, read-only 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% (url: 'Full public URL to test'; strategy: 'Device profile Lighthouse emulates', default mobile), so the description can lean on the schema. It adds no extra parameter semantics — notably it never mentions the mobile/desktop strategy knob, which materially changes results. 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 names a concrete resource (PageSpeed/Lighthouse analysis of a URL) and enumerates the exact outputs: 0-100 performance and SEO scores plus LCP, CLS, TBT, and the CrUX field category. An agent immediately knows what it gets back. No similar sibling exists (ga4/gsc/merchant tools are unrelated), so differentiation is moot, but the phrasing is still slightly output-centric rather than a clean verb+resource statement.

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?

There is no statement of when to choose this tool versus alternatives or when not to use it. The only conditional remark is the API-key/quota note, which is a prerequisite for access rather than usage guidance. A reader must infer the trigger ('I want to audit a page') entirely from the name.

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 readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description goes beyond them by disclosing the return contents (one boolean per service, token storage backend of os-keyring or file, token ok/error, package version), which is valuable given there is no output 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?

Three sentences, each earning its place: what it reports, when to call it, and what it returns. The purpose is front-loaded and the routing hint follows naturally.

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 must describe returns, and it does so precisely (per-service booleans, token backend, error string, version). For a zero-parameter read-only probe, an agent has everything needed to call and interpret it.

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 takes zero parameters, so the baseline is 4. The description correctly implies a no-argument probe and adds nothing that could conflict with the empty 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 specific diagnostic purpose: reporting which Google services are configured and whether the stored OAuth token is valid. This is clearly distinguishable from all sibling tools, which are data-fetching tools for GA4/GSC/Merchant/GTM, not server diagnostics.

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?

Gives an explicit trigger condition: call it first when another tool returns not_configured or not_authenticated. That is a concrete routing rule an agent can act on, though it stops short of naming when-not-to-use or an alternative diagnostic tool.

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