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

With no annotations, the description carries the full burden. It discloses error handling behavior (returns error dict on HTTP 400/403 instead of raising) and the specific dimension used. This adds useful behavioral context beyond what annotations would provide, though it does not mention read-only nature or side effects.

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 sentences, front-loading the purpose, then adding technical detail and error handling. Every sentence adds value with no waste. It is efficiently structured for quick agent scanning.

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?

While the description covers the tool's purpose, technical approach, and error behavior, it lacks critical parameter details and does not mention the output structure (though an output schema exists). Given the tool's moderate complexity (3 params, 1 required) and no annotations, more completeness would be beneficial.

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%, yet the description provides no explanations for the three parameters (days, site, limit). The agent must infer meaning from parameter names alone, which is insufficient. Baseline for no param info is low, and 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?

The description clearly states the tool's function: 'Get queries where AI Overview appearance data is available.' It specifies a unique resource (AI Overview data) and uses a specific verb. Among siblings, none target AI Overviews, making it easily distinguishable.

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 the technical approach (searchAppearance dimension, dataState=all) but does not provide explicit guidance on when to use this tool vs. alternatives like get_search_analytics. The context of siblings implies it is for AI Overview-specific data, but no direct usage boundaries 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?

With no annotations provided, the description carries the full burden and usefully states 'No authentication required', describes fetching robots.txt and checking each known AI crawler agent, and lists verdicts including fetch_error. It does not disclose rate limits, caching, or redirect behavior, but the core behavioral profile is well communicated.

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 front-loaded with the core action, then supplies necessary execution details and a compact verdict legend. Every sentence earns its place with no redundant or vague language.

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?

An output schema exists, so return values need not be explained, and the description covers what is fetched, authentication requirements, and verdict meanings. It is nearly complete, though explicit usage guidance relative to sibling tools would improve it further.

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 clarifies that the url parameter is used to derive an origin by specifying 'for a URL's origin' and showing that only {origin}/robots.txt and {origin}/llms.txt are fetched, which is the key semantic distinction for this single required parameter.

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: checks robots.txt AI crawler access and llms.txt presence for a URL's origin. It clearly distinguishes itself from siblings like ai_overviews_impact by focusing on crawler access files rather than AI Overview 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?

The description implies usage by stating the exact audit it performs, but it does not name alternative tools, when to prefer them, or when not to use this tool. Context is clear enough for a specialized audit, yet explicit routing guidance is absent.

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. Describes the z-score algorithm, threshold default, and return values. Adequately explains what the tool computes without hiding side effects (none apparent). Could be more explicit about read-only nature, but acceptable.

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 concise sentences, front-loaded with purpose, method, and output. No redundant information.

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 an output schema exists (not shown), description adds expected return fields. Explains algorithm and parameters well enough for a statistical tool. Lacks mention of pagination or limits, but not critical for this use case.

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 0%, but description adds context for 'days' (baseline size) and 'threshold' (z-score cutoff). However, 'site' parameter is not explained. Partially compensates for 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?

Clearly states it detects statistically abnormal click days using z-score analysis. Specifies criterion (abs(z_score) > threshold) and outputs. However, does not explicitly differentiate from sibling tools like traffic_drops or check_alerts, though the method is distinct.

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?

Provides guidance on parameter usage ('Use days=90 or more for meaningful baseline statistics') but does not specify when to use this tool versus alternatives like check_alerts or traffic_drops. No 'when not to use' 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes a read operation ('inspect', 'returns fields') but does not elaborate on side effects, rate limits, or what happens on invalid input. It references 'inspect_url' behavior, which adds some context but insufficiently covers all 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 with no extraneous information. Every word serves a purpose; highly 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?

Output schema exists, so return value documentation is handled. The description covers the tool's purpose and relationship to 'inspect_url'. However, it could briefly note error handling for individual URLs in the batch or prerequisites (e.g., site must be verified). Still, it is mostly sufficient for a simple batch wrapper.

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 adds a constraint on the 'urls' parameter ('up to 10') and implies 'site' is a GSC property, but does not describe the format or range of values. Some meaning is added beyond the schema, but not thoroughly.

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 'inspect up to 10 URLs at once in GSC', specifying a specific verb, resource, and scope. Distinguishes itself from the sibling 'inspect_url' by implying batch vs single URL inspection.

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?

Implies when to use (multiple URLs) but does not explicitly state when not to use (e.g., for single URL use inspect_url) or provide alternative tools. The description is adequate but lacks explicit 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?

With no annotations, the description carries the full burden of behavioral disclosure. 'Decode' weakly implies a read operation, but there is no statement about safety, permissions, rate limits, mutation risk, or what the synthetic-fixture contract entails.

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?

It is a single sentence with no wasted words, but it is cryptic rather than self-contained. The sentence does not earn its place because the key term 'synthetic-fixture contract' remains unexplained.

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 two-parameter tool with no annotations and no parameter descriptions, the definition is completely inadequate. It does not explain what flags are returned, how the contract works, or how to interpret the required site input.

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% for both parameters (site, limit), and the description adds no meaning about what 'site' expects or what 'limit' controls. The description fails to compensate for the absent schema 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?

States a verb (Decode) and resource (Bing crawl issue flags), which distinguishes it from siblings like bing_crawl_stats and bing_crawl_settings_get. However, the phrase 'synthetic-fixture contract' is opaque jargon that does not clarify what the tool actually does or what 'flags' are decoded.

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 bing_crawl_stats or bing_url_info. No context, prerequisites, or exclusions 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?

No annotations are provided, so the description carries the full behavioral burden. It discloses only that the return is narrowed to a single value; it says nothing about permissions, whether the value can be absent, or what 'partial contract' implies about data completeness.

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 with no filler or redundancy. It is efficient, though the trailing 'partial contract' clause costs clarity rather than adding it.

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?

An output schema exists, so return structure needn't be explained, but the lone parameter is undocumented and there is no usage context for a tool embedded in a dense Bing/SEO toolset. The definition is too thin for the agent to invoke confidently.

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% and the sole required parameter, 'site', is never mentioned in the description. The description does not compensate for the undocumented parameter, so the agent gets no signal about what 'site' should contain.

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 states a specific verb and resource: return Bing's observed crawl-rate value. The word 'only' distinguishes it from broader crawl tools like bing_crawl_stats or bing_crawl_issues. However, the phrase 'from the partial contract' is unexplained jargon that muddies what the tool actually reads from.

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 when-to-use guidance is given, and no alternative is named despite many adjacent siblings (bing_crawl_stats, bing_crawl_issues, bing_url_info). An agent must guess whether this narrow getter or a broader crawl tool is appropriate.

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 carries the full burden. It implies a read-only lookup but says nothing about auth requirements, rate limits, date granularity, or whether the window is measured from today or from a fixed crawl date. For a stats tool with zero annotation coverage this is a 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?

A single front-loaded sentence with no filler. It is efficient, though the phrase 'dated ... local window' is slightly ambiguous for such a short string.

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?

An output schema exists so return values need not be explained, but with 0% parameter coverage and no annotations, the definition leaves the agent without enough information about the required 'site' argument or what the days window means. For a 2-parameter tool that is a meaningful omission.

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 neither 'site' nor 'days' is documented anywhere. The description hints that 'days' defines the window via 'local window' but does not clarify the format of 'site' (domain vs. URL vs. verified property) or whether days is inclusive. It does not compensate for the documentation gap.

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 (Return) and resource (Bing crawl counts) and scopes it to a dated local window, which distinguishes it from sibling stats tools like bing_query_stats or bing_page_stats. However, it never explicitly contrasts itself with the neighboring Bing crawl tools (bing_crawl_issues, bing_crawl_settings_get), so differentiation is inferred rather than stated.

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 mention of prerequisites (e.g., site must be a verified Bing property), and no routing to alternatives such as bing_crawl_issues for problem diagnosis. The agent must guess the context in which crawl counts matter.

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, but it only says 'Return,' implying a read. It does not disclose auth needs, rate limits, whether data is live or cached, pagination behavior, or any safety profile for a tool requiring site and feed_url.

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 front-loaded sentence with no filler. Its brevity is appropriate, though the vague wording limits usefulness rather than 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?

An output schema exists, so return values need not be explained. However, with no annotations and 0% parameter description coverage, the description omits the role of the required site/feed_url inputs and any usage context, making it inadequate for correct invocation.

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% for two required parameters, and the description never mentions site or feed_url. It adds no meaning beyond the bare parameter names, leaving the agent without guidance on what values to supply.

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 'Return' and resource 'Bing feed-detail row,' but the phrase 'observed list response' is opaque and does not clearly distinguish this from sibling bing_feeds_list or explain what the detail rows contain. An agent gets only a partial sense of purpose without any mention of site or feed_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 explicit when-to-use guidance, no alternatives named, and no prerequisites. The phrase 'observed list response' faintly implies this follows a list call, but the usage context remains implicit and unstated.

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 carries the full behavioral disclosure burden. It correctly signals a destructive removal operation and a confirmation requirement, but does not state permissions needed, reversibility, or what happens if confirmation is absent.

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, front-loaded sentence with no filler. Every word contributes to the purpose and the confirmation condition.

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 destructive mutation tool with no annotations and 0% parameter description coverage, the definition is too sparse. Although an output schema exists and return values need not be explained, the description still omits authentication needs, side effects, and parameter semantics.

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% for three parameters. The description only implies the 'confirm' behavior and mentions a feed, but provides no meaning for 'site' or 'feed_url', so it does not compensate for the missing schema 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 states a specific verb and resource: removing a registered feed, with the scope narrowed to same-origin feeds. It is distinguishable from sibling bing_feeds_list and bing_feed_details by the destructive action, though it does not explicitly name those alternatives.

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 says removal should happen 'only after explicit confirmation,' which is a usage condition, but it gives no explicit when-to-use guidance relative to sibling tools like bing_feeds_list or bing_feed_details. The context is implied 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It hints at field selection ('observed, non-indexation fields') but never defines what that excludes or why, and gives no auth, rate-limit, or pagination 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?

It is a single short sentence, which is efficient, but the opaque 'observed, non-indexation fields' clause consumes the only content slot without conveying actionable meaning.

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?

An output schema exists, so return values need not be described. Still, for a 1-param tool with zero schema coverage and no annotations, the description is too thin to guide correct invocation.

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 single required 'site' parameter has 0% schema description coverage, so the description must compensate and does not. It adds no meaning about what 'site' should contain or how it is identified.

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 clear verb+resource ('Return Bing feeds'), so the basic operation is identifiable. However, the qualifier 'only the observed, non-indexation fields' is unexplained jargon and does not distinguish it from the sibling bing_feed_details, leaving the actual scope ambiguous.

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 use this versus the closely related bing_feed_details, bing_feed_submit, or bing_feed_remove. The agent must infer that this is the listing counterpart purely 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?

No annotations are provided, so the description carries the full burden. It usefully discloses that the operation does not claim indexation, but omits permissions/auth requirements, rate limits, and what happens on duplicate submissions.

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 with no wasted words; scope and the key caveat are both present immediately.

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?

An output schema exists, so return values need not be described. However, with zero annotation coverage and 0% schema description coverage, the description leaves auth, failure modes, and parameter formats unaddressed for a write operation.

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% across two params. The phrase 'same-origin feed' implies feed_url must share the origin of site, which adds some meaning beyond the bare 'site'/'feed_url' property names, but neither parameter's format is explained.

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 (Submit) and resource (feed to Bing), and the qualifier 'same-origin' narrows scope meaningfully. It is distinguishable from siblings like bing_feed_remove and bing_url_submit, though it never names them directly.

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?

'Submit one same-origin feed' implies usage constraints (single feed, same-origin) but gives no explicit when-to-use guidance or named alternatives such as bing_url_submit or submit_sitemap. The agent must infer the routing.

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 carries the full behavioral burden. It does not state that this is a read-only operation, whether it needs Bing auth, rate limits, or what "synthetic shape" implies (possibly non-live/sample data, which is a significant caveat left unexplained).

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?

It is a single short sentence, so it is not bloated. However, "from a synthetic shape" spends the one sentence's budget on confusing filler rather than front-loading the useful scoping information.

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?

An output schema exists, so return values need not be spelled out, which lightens the burden. But with no annotations and 0% parameter coverage, the description should still disclose read-only status, data provenance (the "synthetic" caveat), and pagination semantics; it omits all of these.

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 for both parameters (page, site) and does not. "One Bing page" loosely maps to the page param, but there is no explanation of what a page contains, zero-vs-one-based paging, or what format the site argument expects.

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 verb ("Return") and resource ("Bing page of backlink counts"), which is better than a tautology. But "from a synthetic shape" is opaque jargon that does not clarify what data is actually returned, and there is no differentiation from close siblings like bing_url_links or link_equity_map. An agent cannot confidently tell which of these 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?

There is no explicit when-to-use, when-not-to-use, or alternative tool named. "One Bing page" hints at pagination but gives no guidance on how this differs from bing_url_links or bing_url_info. The agent is left to infer usage 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?

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing about authentication requirements, rate limits, data freshness/lag, or behavior when no query data exists for the page. The only behavioral signal is the single-page scope, which is minimal for an external API call.

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?

It is a single front-loaded sentence with no filler or redundancy, which is structurally clean. The terseness, however, is under-specification rather than discipline, so it does not reach the top of the scale.

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?

An output schema exists, so return values need not be described. But with no annotations, 0% parameter coverage, and no usage or prerequisite context, the definition is too thin for a 4-parameter external-API tool whose siblings overlap heavily.

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% across 4 parameters. The description only loosely implies the page parameter ("one requested page") and site via "Bing"; days and limit (both with defaults of 30 and 1000) are undocumented in either the schema or the description, leaving the agent guessing at their 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?

The description states a verb ("Return") and a resource (Bing query performance) scoped to "one requested page," which is more than a restatement of the name. However, "query performance" is left undefined (impressions? clicks? CTR? position?), and it does not distinguish this tool from close siblings like bing_page_stats or bing_query_stats.

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 (e.g., the site must be verified in Bing Webmaster Tools), and no named alternative. The phrase "one requested page" implies a single-page scope but never tells the agent when to prefer bing_query_stats or bing_page_stats instead.

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 carries the full behavioral burden. It discloses the page-normalization behavior, but says nothing about auth requirements, rate limits, default window behavior, pagination, or how the 'Query to page' rollup affects returned rows. For a stats tool with zero annotation coverage this is a significant 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?

A single, front-loaded sentence with no filler. It is efficient, though arguably too terse for a tool with three undocumented parameters and no annotations.

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?

An output schema exists, so return values need not be explained. However, for a stats tool with no annotations, 0% parameter coverage, and no usage routing, the description leaves the agent without enough to select it confidently over the several Bing/analytics siblings.

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% across three parameters (site, days, limit), and the description adds no meaning for any of them. It never clarifies what 'site' format is expected, that 'days' is the lookback window, or what 'limit' caps. The intuitive parameter names are the only guide, so the description fails to compensate for the coverage gap.

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 ('Return Bing page performance') and adds a scoping note ('normalizing Bing's Query field to page') that implicitly distinguishes it from bing_query_stats and bing_page_query_stats. The purpose is clear, though it does not name the sibling alternatives explicitly and never says which metrics 'performance' includes.

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 when-to-use guidance and no alternatives named. The agent must infer from the phrase 'normalizing ... to page' that this is the page-level aggregation tool versus bing_query_stats or bing_page_query_stats. No prerequisites or exclusions are 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?

No annotations are provided, so the description carries the full behavioral burden. It hints that results are scoped to a 'rolling window,' but says nothing about required auth/permissions, how the window is computed, rate limits, or whether results are paginated — a large gap for a zero-annotation 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?

A single tight sentence with no filler, and the key scoping concept (rolling window) is front-loaded. It is efficient, though its brevity comes partly from omission rather than precision.

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?

An output schema exists, so return values need not be described. But with no annotations and 0% parameter coverage, the description leaves the meaning of 'site' and 'limit' and the tool's relationship to sibling Bing stats tools unexplained, so the agent lacks enough to invoke it confidently.

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 for all three parameters. 'Rolling window' loosely maps to the 'days' parameter, but 'site' and 'limit' receive no explanation of format, required-ness, or effect on results.

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 states a specific verb ('Return') and resource ('Bing query performance'), so the agent knows this is a read/report tool. However, it gives no differentiation from the many nearby siblings such as bing_page_query_stats, bing_page_stats, and bing_rank_traffic_stats, leaving the agent to guess which Bing stats tool applies.

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, when-not-to-use, or alternative-tool guidance. The mention of a 'rolling window' implies time-based reporting but does not tell the agent when this tool is preferable to the other Bing stats siblings.

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 carries the full disclosure burden. It hints at an output-honesty constraint ('without inventing rank fields') but omits auth requirements, the scope/granularity of the daily aggregation, and any rate or data-freshness behavior for a mutation-free but underspecified 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?

A single compact sentence with the core action front-loaded. It is tightly sized, though the trailing clause about rank fields is cryptic and consumes space that better parameter or usage guidance could have used.

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?

An output schema exists, so return values need not be explained, but with zero annotations, 0% schema description coverage, and no usage routing, the definition leaves an agent unable to distinguish this tool from its numerous Bing-stats siblings.

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% for two parameters. The word 'daily' loosely gestures at the 'days' parameter and 'Bing' gestures at 'site', but the description never explains the site value format or the window semantics, so it does not compensate for the coverage gap.

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: 'Return Bing daily clicks and impressions.' An agent can grasp the core purpose, though it never differentiates itself from close siblings such as bing_page_stats, bing_query_stats, or bing_url_traffic, so the boundary is left to inference.

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 named alternative among the many competing Bing stats tools. The only operative instruction is a negative warning ('without inventing rank fields'), which does not tell the agent when this tool is the right choice.

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 zero annotations, the description carries the full behavioral burden. 'Return' implies a read, and 'verified-state' hints at the payload's verification field, but there is no mention of auth requirements, rate limits, pagination, or account-scoping behavior. Given no annotations, this is a significant 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?

A single front-loaded sentence with no wasted words. 'verified-state summaries' is slightly jargon-heavy but the statement stays tight and purposeful.

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?

An output schema exists, so return-value documentation is unnecessary, and with no parameters the call surface is trivial. The description is nearly sufficient for such a simple enumeration tool, missing only usage/routing context.

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 compensate for; the baseline for a 0-parameter tool is 4.

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 (return) and resource (sites), with scope qualifiers 'verified-state summaries' and 'visible to the Bing account'. It is distinguishable from siblings like get_site_details (single site) and list_properties (different provider), though it never names an alternative explicitly.

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 when-to-use guidance, no prerequisites, and no named alternatives. The agent must infer that this is the entry-point enumeration tool from the name alone; the description adds no routing logic relative to siblings such as list_properties or get_site_details.

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 present, so the description carries the burden, but it is short. It does disclose one genuine behavioral trait: results are limited to observed fields and make no indexation claims, which usefully signals the tool's epistemic limits. It says nothing about authentication, rate limits, or data freshness, and the presence of an output schema offloads return-value 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?

A single, front-loaded sentence with no filler or repetition. It is efficient, though its brevity reflects under-specification rather than tight editing of rich content.

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 two-required-parameter tool with 0% schema coverage, no annotations, and many closely related Bing siblings, the description is too thin. The output schema excuses it from explaining return values, but it still lacks parameter meaning, usage routing, and any operational context.

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% and both required parameters (site, url) are undocumented in the schema. The description adds no meaning about what "site" is (hostname, property, Bing site ID?) or how it differs from "url", leaving a real gap the description was expected to fill.

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?

"Return only fields observed from Bing URL info" largely restates the tool name (bing_url_info) rather than defining a distinct capability. The only added information is a negative caveat ("without indexation claims"), which is a scope limitation, not a purpose statement. It does not distinguish this tool from close siblings like bing_url_traffic, bing_url_links, or 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?

No when-to-use guidance, prerequisites, or named alternatives are provided. The phrase "without indexation claims" faintly implies a use case (raw observed data rather than an indexing verdict), but the agent is left to infer this and cannot tell when to pick this over the many other Bing/URL inspection 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?

No annotations are provided, so the description carries the full burden. It implies a read-only operation via 'Return' and scopes the output to 'one Bing page,' which hints at pagination behavior, but it does not disclose authentication requirements, rate limits, or any side effects. This is adequate but leaves meaningful behavioral gaps for a tool with zero annotation coverage.

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, front-loaded sentence with no wasted words. It efficiently communicates the core operation without redundant or filler content.

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?

An output schema exists, so return values need not be described. However, with no annotations and 0% schema description coverage, the description should do more to explain parameters and usage. It covers the basic purpose but leaves the required 'site' parameter and any usage context unexplained, making it only partially complete 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?

Schema description coverage is 0%, so the description must compensate. It clarifies that 'url' is the target URL and that 'page' implies pagination ('one Bing page'), but it completely omits any explanation of the required 'site' parameter, which is essential for invocation. Coverage is partial and insufficient.

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 states a specific verb ('Return') and resource ('Bing page of backlinks for the requested target URL'), making the tool's function clear and distinguishable from sibling tools like bing_link_counts. It does not explicitly reference alternatives, but the resource and scope are precise enough for an agent to select it correctly.

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 guidance on when to use this tool versus alternatives such as bing_link_counts or bing_url_info. It only states what it returns, leaving the agent to infer the appropriate context without any exclusions or prerequisites.

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 carries the full burden of behavioral disclosure. It adds one behavioral fact—the tool may refuse when quota semantics are unknown—but omits what preflight checks, whether URLs are actually submitted, side effects, permissions, and error 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?

The single sentence is brief but structurally under-specified; it front-loads 'Preflight a Bing URL batch' but then trails into an unclear refusal clause. It is not verbose, but the wording does not earn its place because it fails to orient the agent.

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 annotations, no parameter descriptions, and only a cryptic one-line description, the definition is not complete for a submission/batch tool. Although an output schema exists and need not be explained, the input contract and the tool's actual behavior remain undocumented.

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% and the description provides no meaning for 'site' or 'urls'. It does not explain the expected URL format, whether 'site' is a Bing property identifier, or any constraints on the batch, leaving both required parameters undocumented.

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 resource ('Bing URL batch') but its stated purpose is ambiguous: 'preflight' and 'refuse' do not match the tool name 'submit_batch' and leave unclear whether the tool submits URLs or only blocks submission. It does not distinguish this tool from siblings like bing_url_submit, submit_batch, or bing_url_submission_quota.

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. The phrase 'while quota semantics are unknown' hints at a refusal condition but does not tell an agent when the tool should be called, what prerequisites are needed, or which sibling to use instead.

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 does add one genuinely useful behavioral caveat: the returned integers should not be interpreted as total or remaining values, which warns the agent away from a common misreading. However, it says nothing about auth requirements, rate limits, or freshness of the quota data.

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 sentence with no padding, which is appropriately sized for a simple read. But the phrasing ('without claiming total or remaining semantics') is cryptic and spends its only clause on a negative disclaimer rather than a positive statement of behavior.

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?

An output schema exists, so return-value explanation is not required, but the description still omits the parameter meaning and any usage context. For a tool whose whole value is a quota check, an agent is left guessing what 'site' must contain and when the call is warranted.

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% and the single required parameter 'site' is never mentioned in the description. The description does not clarify whether 'site' is a domain, a verified property identifier, or a Bing site ID, so it fails to compensate for the schema gap.

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 verb and resource (return Bing quota) but is oddly framed around what it does not claim rather than what it does. An agent can infer this reports URL submission quota, but it never says whose quota or that it is scoped to the given site, and it does not differentiate from siblings like bing_url_submit or bing_urls_submit_batch.

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 indication of when an agent should check quota before submitting, and no mention of the obvious alternatives (bing_url_submit, bing_urls_submit_batch, bing_feed_submit). The description gives no routing context at all.

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 behavioral burden, and it discloses one genuinely useful non-obvious fact: submission does not guarantee or assert indexation. However, it omits quota/rate-limit behavior (a sibling, bing_url_submission_quota, implies quota exists), whether site ownership/verification is required, and what happens on rejection.

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 with no filler; the scope qualifier and the indexation caveat are both packed in without 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?

An output schema exists so return values need not be described, but for a submission (write) tool with zero annotation coverage and 0% parameter documentation, the definition leaves too much open: no auth/verification requirement, no quota expectation, and undefined 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% for both required parameters, so the description must compensate. 'Same-origin URL' and 'site' together imply the URL must belong to the site's origin, which is a meaningful constraint, but neither parameter is defined (format, whether site is a domain vs. a verified property, whether URL must be absolute).

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 ('Submit one ... URL to Bing') and the 'one' framing distinguishes it from the batch siblings like bing_urls_submit_batch and submit_batch. It also pins a scope constraint ('same-origin'). It stops short of naming the alternative tools, but an agent can still tell what it does.

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 when-to-use or when-not-to-use guidance, and none of the competing submission paths (bing_urls_submit_batch, indexnow_submit, submit_sitemap, bing_feed_submit) are referenced. The 'without claiming indexation' caveat hints at expectations but does not route the agent between 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?

No annotations, so the description carries the full behavioral burden. It implies a read ('observed traffic') but never states read-only status, auth requirements, or what 'observed traffic' actually measures (impressions vs. clicks) or the CTR derivation window. Only 'derived CTR' adds any behavioral 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?

A single front-loaded sentence with no filler or repetition. It is efficient, though its brevity is partly under-specification rather than true 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?

An output schema exists, so return values need not be explained. But with no annotations, zero parameter documentation, and no usage routing against the many bing_* siblings, the definition leaves too much unspecified for an agent to invoke it confidently.

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?

Two required parameters ('site', 'url') at 0% schema description coverage, and the description says nothing about either — no expected format, no site/url relationship. With no compensation in the description, the agent cannot tell what values are valid.

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 ('Return') and resource ('observed URL traffic and derived CTR'), and the clause 'without rank fields' implicitly distinguishes it from the rank-bearing sibling bing_rank_traffic_stats. It is clear what it returns, though it doesn't state what the tool is used for.

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 when-to-use guidance and no named alternatives. 'Without rank fields' hints at a contrast with bing_rank_traffic_stats / bing_page_stats but never says which sibling to pick or under what condition, leaving the agent to infer routing from sibling names alone.

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 carries the full disclosure burden. It does reveal meaningful behavioral detail — the 50%-of-clicks and >5000-impressions-at-position->10 thresholds plus severity levels — but says nothing about read-only vs mutating nature, permissions, or rate limits.

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?

Front-loaded with the one-line purpose, then two tightly-worded clauses that each define an alert and its trigger. No filler sentences and every clause carries information.

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?

An output schema exists, so return format needn't be described, and the alert logic is well covered. However, for a three-parameter tool with no schema descriptions, the complete silence on parameters leaves a real gap for correct invocation.

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% and the description never references any of the three parameters (site, days, engine). With the schema supplying no semantics, the description should compensate but does not, leaving 'days' and 'engine' entirely undefined.

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 gives a specific verb ('Scan') and resource ('structural SEO risks') and enumerates exactly the two alert types produced with their thresholds. It is clear what the tool does, though it does not explicitly contrast itself with close siblings like traffic_health_check or analytics_anomalies.

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 and no mention of alternatives, despite several overlapping siblings (traffic_health_check, analytics_anomalies, traffic_drops, seo_striking_distance). The agent must infer when this scan is preferable to those.

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 and does disclose meaningful behavior: a hard 10-URL cap, that non-problem URLs are suppressed from results, and the full category taxonomy returned. It does not say what happens if more than 10 URLs are supplied (error vs truncation), nor any auth or rate-limit 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?

Two tight sentences plus a category enumeration, front-loaded with the tool's behavior before the alternative. Every element (cap, filter, categories, alternative) 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?

An output schema exists, so return-value detail is not required, and the description still summarizes the response shape. The gaps are the undocumented 'site' parameter and undefined behavior when the URL list exceeds the stated cap, which matter for a two-parameter tool with no annotations.

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 for both parameters. It adds the 10-URL ceiling for 'urls', but says nothing about 'site' — its expected format, whether it is a domain or a search-console property, or how it scopes the inspection — leaving a required parameter undocumented everywhere.

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 (inspect URLs for indexing issues), the scope cap (up to 10), and the filtering behavior (return only problem URLs plus a category summary). It also names the sibling it is not (batch_url_inspection), so an agent can distinguish the two without opening either schema.

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 this tool (you only want URLs with indexing problems) and names the alternative with its selecting condition (batch_url_inspection if you need all URLs regardless of status). No inference required.

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 carries the full behavioral burden. It discloses important constraints: deltas only appear when both providers expose the same exact observed window, and positions remain side-by-side due to different provider semantics. It does not address permissions, rate limits, or read-only nature, but the key comparability caveats are surfaced.

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 tightly written: one sentence for purpose, one for delta behavior, one for position semantics. It is front-loaded with the core action and contains no 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?

An output schema exists, so return values need not be explained. The description adds meaningful comparison caveats, but it leaves all input parameter semantics undocumented and provides no usage context. For a 5-parameter tool with 0% schema description coverage and no annotations, this is only minimally 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 description coverage is 0% across 5 parameters. The description vaguely hints at the dimension values by saying 'query or page metrics,' but it does not name or explain google_site, bing_site, days, limit, or dimension. With no parameter descriptions in the schema, 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?

The description states a specific verb and resource: comparing Google and Bing query or page metrics. It is clear enough to distinguish from most sibling tools like compare_search_periods, but it does not explicitly name any alternative or sibling to differentiate from.

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 a caution about causality and comparability but does not say when to use this tool versus alternatives such as bing_query_stats, bing_page_stats, or get_search_analytics. No prerequisites, exclusions, or routing guidance 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 reveals a 3-day lag and explains the period definitions. It does not mention authentication or permissions, but the read-only nature is implied.

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 extremely concise: three sentences, front-loaded with the main purpose, and every sentence adds value 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?

Given the output schema exists and the tool is simple, the description adequately explains the comparison logic, lag, and use case. Minor edge cases are not covered.

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 explains the 'days' parameter in context (e.g., 7 for weekly trends) but does not mention the 'site' parameter, leaving partial 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 clearly states the tool compares two consecutive equal-length windows and reports delta in clicks and impressions, which distinguishes it from sibling analytics tools that provide raw 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 explicitly states it is useful for week-over-week or month-over-month trends, providing context for when to use it. However, it does not list alternatives or when not to use it.

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 provided, the description must carry the burden. It reveals key behaviors: URL normalization, top-20 sorting, GA4 error handling, and question classification. However, it omits details like rate limits, auth requirements, or behavior on missing 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?

The description is relatively concise and well-structured with clear steps. However, it includes implementation details (e.g., _normalize_url, try/except) that could be condensed without losing clarity.

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 moderate complexity (combining GSC and GA4) and the existence of an output schema (which relieves the need to describe return values), the description provides a reasonable overview. It lacks specifics on parameter input formats and edge case handling.

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 mentions the four parameters (days, site, page_url, property_id) and hints at URL normalization, but does not explain formats, allowed values, or constraints beyond defaults.

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: 'Gather SEO content intelligence for a single page: top queries, question queries, and GA4 engagement.' It specifies the output components and distinguishes from sibling tools that focus on raw search analytics or GA4 alone.

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 usefulness for 'brief-writing, content refreshes, and intent analysis' and outlines steps, but does not explicitly state when to avoid this tool or compare it to alternatives like get_search_analytics or ga4_page_performance.

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 and does substantial work: it discloses the fetch-and-extract pipeline (network egress to an arbitrary URL), the absence of auth/Google API dependency, and the scoring internals. Listing the verdicts including 'fetch_error' also surfaces the failure mode. It stops short of stating rate limits, timeouts, or behavior on paywalled/JS-rendered 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?

Front-loaded with the one-line purpose, then progressively finer detail, which is good structure. The filler-phrase attribution line ('adapted from claude-seo (agricidaniel, MIT)') is provenance noise that doesn't help an agent decide or invoke, keeping this just under full marks.

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?

An output schema exists, so the description needn't explain return values, yet it still volunteers the verdict enum as useful context. With only one input parameter and no annotations, the definition covers what an agent needs to invoke it correctly; only fetch-failure and timing behavior remain 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?

Schema description coverage is 0% for the single 'url' parameter, so the description must add meaning — 'Fetches the URL, extracts visible text' usefully implies this must be a live, fetchable page URL rather than an ID or path. That is helpful but thin; it gives no format hints (scheme, trailing slash, canonicalization) or whether redirects are followed.

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 verb and resource (analyse page content quality) and enumerates the exact scoring signals — thin content, filler language, information density, bigram repetition — under a stated framework (Google QRG / E-E-A-T). This is sharply distinct from siblings like content_brief, heading_audit, or page_technical_audit, so an agent can route correctly even without an explicit sibling callout.

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 (you run this on a live page to grade content quality), and the 'No Google API calls. No authentication required.' line pre-empts a common prerequisite question. However, it never states when to prefer this over content_brief or how it relates to the other audit tools, and there are no explicit exclusions or preconditions beyond the URL.

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 carries the burden. It discloses the return format (p75 per week, oldest to newest), the metrics available, and the API key requirement. However, it does not mention rate limits, error handling, or behavior for URLs with no data.

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 with three focused sentences. The first sentence states the core purpose, the second details parameter options, and the third mentions return format and requirement. No redundant information.

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 covers the key aspects: what data is returned (p75 per week), the parameters, and the environment variable requirement. An output schema exists but is not shown; the description provides sufficient context for an agent to use 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 0%, so the description must compensate. It explains form_factor options (ALL_FORM_FACTORS, PHONE, DESKTOP, TABLET) and lists metric values explicitly. The url parameter is not described beyond being a string, but the overall parameter meaning is clear from the tool's purpose.

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 'Fetch 40 weeks of Core Web Vitals history for a URL from the CrUX History API.' It specifies the action (fetch), the resource (Core Web Vitals history), and the scope (40 weeks), distinguishing it from siblings like crux_page_vitals.

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 parameter options (form_factor, metric) and the required environment variable CRUX_API_KEY. However, it does not explicitly state when to use this tool instead of alternatives such as crux_page_vitals or other analytics 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?

No annotations are provided, so the description carries the full burden; it discloses the CRUX_API_KEY requirement and enumerates outcome states (good/needs_improvement/poor/not_enough_data/missing_key/fetch_error), which warns the agent about auth and data-availability failures. It does not cover rate limits or latency, so it is strong but not exhaustive.

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?

Front-loaded with purpose and return values, then the parameter and environment details. The trailing attribution line ('Adapted from claude-seo lcp_subparts.py') is minor noise but the body sentences each earn their 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?

An output schema exists, yet the description still tells the agent what comes back (four p75 subparts plus dominant phase) and the verdict states, plus the credential requirement. Nothing needed 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 0%, so the description must compensate. It fully enumerates the form_factor values and default, which the schema does not, though it adds nothing about the url parameter (self-evident, but the schema is bare).

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 (decompose) and resource (LCP subparts) with the mechanism (CrUX API) and outcome (four named subparts). It is clearly distinguishable from siblings like crux_page_vitals and crux_history.

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?

Explains the diagnostic context clearly — turning an aggregate LCP number into a specific phase to fix. It does not explicitly name alternate tools (crux_page_vitals, pagespeed_audit, preload_audit) or state when to prefer them, so it stops short of full routing 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?

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that it requires a CRUX_API_KEY environment variable, returns p75 percentile and ratings, and handles insufficient data with a 'not_enough_data' verdict. It lacks mention of read-only nature, rate limits, or error handling, but covers the essential 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?

The description is concise and well-structured, leading with the core purpose, then detailing return format, edge cases, and prerequisites. Every sentence adds information 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?

The description covers the tool's purpose, parameters, return format (p75 and ratings), edge case (insufficient data), and prerequisite (API key). With an output schema present, the lack of detailed return structure explanation is acceptable. Minor omissions like rate limits or error codes prevent a perfect score.

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?

Since schema description coverage is 0%, the description compensates by specifying the allowed values for form_factor ('ALL_FORM_FACTORS' | 'PHONE' | 'DESKTOP' | 'TABLET') and noting that url is required. It could further clarify the expected URL format (e.g., fully qualified), but adds significant value 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 fetches current Core Web Vitals (LCP, INP, CLS, FCP, TTFB) for a URL from the CrUX API, establishing a specific verb and resource. However, it does not explicitly distinguish itself from the sibling tool 'crux_history,' which likely provides historical data, missing an opportunity for differentiation.

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 guidance on when to use this tool versus alternatives like 'crux_history' or other analytics tools. It does not mention when not to use it or any prerequisites beyond an API key, failing to help the agent choose appropriately.

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 carries the full burden. It discloses the basic purpose but does not mention whether the tool is read-only, any permission requirements, rate limits, or pagination behavior. The 'limit' parameter suggests paginated results but is not explained.

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 is efficient and front-loaded, providing the essential purpose without any 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?

The tool has an output schema (not shown) so return values are covered. However, with three parameters and no annotations, the description should at least explain the parameters. Given the simplicity and presence of output schema, the description is minimally complete but leaves gaps in parameter understanding for an 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?

The description adds no information about the three parameters (days, site, limit). The schema has 0% description coverage, and the parameter names are only titled; the description does not explain their meaning, default values, or allowed formats. For an AI agent, this lack of guidance could lead to incorrect usage.

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 Discover performance data (top pages by impressions) and explicitly notes that Discover does not support the query dimension, distinguishing it from search analytics tools. This gives a specific verb+resource and differentiates from siblings.

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 the use case is for Discover performance reporting. The note about the query dimension indirectly suggests not to use this tool for query-based analysis, which would be handled by tools like get_search_analytics. However, it does not explicitly state when to use this tool over others or provide 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?

With no annotations, the description carries the full burden and does well: it discloses the fetch side effect, that results are persisted to a local SQLite database as a 'known good' reference, that no Google API calls are made, and that CWV capture requires CRUX_API_KEY and is skipped without it. This is meaningful behavioral context, though error/failure behavior on unreachable pages is not covered.

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?

Front-loads the purpose, then the mechanics and caveats, with no filler in the operational sentences. The provenance line about drift_baseline.py / Dan Colta methodology is arguably extraneous but is short and bounded.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers purpose, side effects, dependency, and the follow-up tool. It is nearly complete; only the sibling-routing detail (versus drift_history) and failure handling are absent, which are minor for a baseline-capture 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 coverage is 0%, so the description needs to compensate for two undocumented parameters. It indirectly clarifies skip_cwv by explaining that CWV capture requires CRUX_API_KEY and is 'skipped otherwise,' and url's role is self-evident, but neither parameter is named or given format/type details. Partial compensation warrants a mid score.

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 ('Capture an SEO baseline snapshot for a URL') and immediately enumerates what it extracts, so an agent knows exactly what this produces. It also names the sibling it pairs with (drift_compare), distinguishing it from that tool without opening either schema.

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 clear sequencing guidance ('Call drift_compare later to detect regressions'), which establishes the baseline-then-compare workflow with the sibling drift_compare. It stops short of stating when NOT to use it (e.g. versus drift_history or when a baseline already exists), so it is clear but not exhaustive.

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 behavioral burden and adds useful context: 17 rules with severity tiers, old/new values, recommended actions, no Google API calls, and the CRUX_API_KEY dependency. It still does not state read-only safety explicitly or describe auth/rate-limit behavior, so it is strong but not complete.

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 definition is front-loaded and mostly efficient, with the core purpose and prerequisite stated early. The attribution line about claude-seo/Dan Colta/MIT does not help an agent invoke the tool and is the main non-essential sentence.

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 output schema covers return values, and the description explains the comparison rules, severity model, and CWV dependency well. However, for a 3-parameter tool with 0% schema description coverage, it leaves baseline_id and skip_cwv insufficiently explained, so the definition is only partially 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 description coverage is 0%, so the description must explain the three parameters. It implies the URL is the target and hints at CRUX/CWV behavior, but it never explains baseline_id or skip_cwv, leaving key parameters semantically undocumented.

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 first sentence names a specific verb and resource: comparing current page state against a stored baseline to report SEO drift. It clearly distinguishes the tool from general page-analysis siblings by focusing on baseline comparison and drift findings.

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 says to call drift_baseline first if no baseline exists for the URL, giving a clear prerequisite. It also notes that CWV comparison requires CRUX_API_KEY and is skipped otherwise, but it does not describe when not to use this tool or name alternative drift 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?

With no annotations, the description carries the full burden. It discloses the return shape (timestamps, triggered finding counts by severity, baseline IDs) and implies a read operation, but says nothing about pagination behavior, the default 10-item cap, or any rate/auth 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?

Two compact sentences, front-loaded with the core action and followed by the sibling disambiguation. Nothing is wasted.

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?

An output schema exists, so detailing return fields is not strictly required, and the read context is adequate. However, for a two-parameter tool at 0% schema coverage, leaving 'limit' undocumented is a real gap.

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% and there are two parameters. The description explains neither the required 'url' nor the optional 'limit' (default 10, page size semantics). It does not compensate for the coverage gap.

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 ('Return recent drift comparisons for a URL'), and the sibling drift_compare is explicitly named, so the agent can distinguish it. Clear, though it does not explicitly label the tool as read-only.

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: use this for history and 'drift_compare to run a fresh comparison.' That is a real when/when-not distinction. It lacks guidance on the limit parameter or freshness windows, but the core routing is present.

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?

Without annotations, the description carries the burden. It discloses sequential report execution and date format, but lacks read-only confirmation, rate limits, or side effect details. This is adequate 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 concise with front-loaded main action, using four clear sentences without 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?

Given 6 parameters, no annotations, and an output schema, the description covers the main usage and report structure well, though it omits error handling or edge cases.

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 0%, so the description must compensate. It explains date relative format, hostname/country filtering, and event_name filter, but does not clarify property_id or provide complete parameter meanings.

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 fetches GA4 conversion data, specifically pages with conversions and event counts, and runs two sequential reports. This distinguishes it from sibling tools like ga4_page_performance or ga4_user_behavior.

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 context by noting it is useful for identifying which pages and events drive goals, but does not explicitly state when to use it versus alternatives or mention exclusions.

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 carries the full burden. It discloses that step 1 conversion_rate is always null and that at least 2 steps are required. It does not mention rate limits or authentication, but the read-only nature of a report tool is implied.

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 (4 sentences), front-loaded with the main purpose, and each sentence adds necessary detail 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 tool with 4 parameters, no schema descriptions, and an existing output schema, the description covers the step structure, output format, and property_id override. It could elaborate on date format but is otherwise 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?

Since the schema has 0% coverage, the description adds meaning by explaining that steps are dicts with 'name' and 'event', and that property_id is optional for overriding defaults. However, it does not detail the date parameters.

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 runs a GA4 funnel report via a specific API, explains the step structure, and mentions output details. However, it does not differentiate from the sibling tool 'ga4_conversion_funnel', which could cause confusion.

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 some context (e.g., overriding property_id for multi-property setups) but lacks explicit guidance on when to use this tool versus alternatives, such as 'ga4_conversion_funnel'.

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 carries full burden. It lists returned metrics (sessions, engaged_sessions, bounce_rate, etc.) which helps understand behavior. However, it does not disclose read-only nature, rate limits, auth needs, or data freshness, leaving gaps.

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 four sentences long, front-loaded with purpose, and each sentence adds value. No fluff or repetition. It is well-structured and easy to parse.

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 parameters) and presence of an output schema, the description covers inputs well and outlines returned data. Minor gaps: limit meaning and error handling are absent, but overall it provides sufficient context for most use cases.

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 0%, but the description adds meaning for most parameters: explains date format (GA4 relative format), property_id override, hostname and country narrowing. Limit is mentioned but not detailed. Overall, it significantly enhances schema understanding.

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 fetches GA4 landing page performance filtered to organic traffic only. It uses specific verbs and resources, and distinguishes from sibling tools like ga4_page_performance and ga4_traffic_sources by narrowing to organic traffic and landing pages.

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 the tool (for organic landing page performance) and includes context for multi-property setups by passing property_id. However, it does not explicitly state when not to use it or mention alternative tools for different scenarios.

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 carries the full burden. It discloses accepted date formats and substring matching for page_path, but fails to mention rate limits, authentication requirements, pagination, or error behavior. Minimal behavioral disclosure beyond basic 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 concise (two sentences plus bullet points), front-loaded with purpose, and every sentence adds value. No fluff or redundancy. Efficiently structured.

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 6 parameters and an output schema, the description lists returned metrics and explains filters and dates, which is helpful. However, it misses explanation for property_id and does not specify acceptable format for country (e.g., code vs name). Adequate but with 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 0%, so the description must compensate. It adds meaning for 5 of 6 parameters: dates (relative format), page_path (substring match), hostname/country (narrowing). Only property_id is omitted. This adds significant value 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 fetches GA4 page-level metrics and lists specific metrics (views, active users, etc.). It identifies the resource and action, but does not explicitly differentiate from sibling tools like ga4_conversion_funnel or ga4_user_behavior, which limits differentiation. A clear verb and resource, but no sibling distinction.

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 context on optional filters (page_path, hostname, country) and date formats, implying usage scenarios. However, it does not offer explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or when not to use it. The guidance is implied but not comparative.

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 discloses grouping behavior (by screen name, country, device category) and parameter nuance for hostname. Could mention auth/rate limits but sufficient for read 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?

Four sentences, each with distinct value. Front-loaded with main action. No redundant 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, grouping, and param usage. Though output schema exists, description could mention it returns active users grouped; still adequate for a realtime monitoring tool.

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