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 and largely fails to. It discloses that results are paginated starting at 0 and sourced from Bing, but says nothing about permissions/verified-property requirements, result shape, ordering, or what the page limit implies for iteration.

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 short sentence front-loading the resource, source, and pagination constraint. Nothing is wasted, though the brevity comes at the cost of the missing guidance captured in other dimensions.

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 output schema, and one of two parameters undocumented, the definition is under-specified for an agent to call it confidently. It does not say what a result item contains or how the paginated list terminates.

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 50%: siteUrl is documented in-schema ('URL exacta de la propiedad verificada') while page is not. The description adds a small amount of meaning by stating pagination starts from 0, matching the schema default, but gives no guidance on the 0-32767 bounds or how to advance pages.

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 concrete resource ('Páginas del sitio con enlaces entrantes') and the data source (Bing), so an agent understands it returns the list of pages that receive backlinks. It is distinguishable in spirit from the sibling bing_backlink_sources, but never names or contrasts that sibling 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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as bing_backlink_sources for the linking side of the data. The only usage hint is the pagination phrasing 'paginadas desde 0', which is implied rather than instructed.

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 only states the data returned. It omits pagination behavior (relevant given the 'page' parameter), the requirement for a verified property, rate limits, and result 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?

A single, front-loaded sentence with no filler or redundancy. It is efficient, though its brevity is closer to under-specification than optimal completeness.

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 3-parameter tool with no annotations and no output schema, the description should explain return content more fully and cover pagination and the verified-property requirement. It leaves significant gaps that an agent would need to guess at.

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 67% and the description adds no parameter meaning at all. The 'page' parameter lacks a schema description and is unexplained here, leaving the reader to infer pagination semantics on their own.

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 identifies the resource returned (URLs and anchor texts linking to a site page) and the data source (Bing). It is a noun phrase describing output rather than an explicit verb, and it does not distinguish itself from the sibling bing_backlink_pages, so it stops short of a 5.

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

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

There is no guidance on when to use this tool versus alternatives such as bing_backlink_pages or bing_url_info. No prerequisites, context, or exclusions are stated despite several closely related Bing 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 burden. It does not disclose the return shape, whether results are paginated, how 'limit' bounds output, or what permission/verified-property requirements exist for a mutation-free but privileged data pull.

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 with no waste, but the brevity is under-specification rather than conciseness — there is no front-loaded scope, return description, or usage condition to earn the space saved.

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 two parameters, no annotations, and no output schema, the description is far too thin: it omits what a 'crawl issue' record contains, ordering, and pagination behavior, all of which the agent needs to call it correctly.

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

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

Schema description coverage is only 50% (siteUrl documented, limit undocumented). The description adds nothing about either parameter, so it fails to compensate for the missing 'limit' semantics such as default 100 / max 1000 and what a limit of 1 returns.

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

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

The description names a specific resource (crawl issues) and source (Bing), so the agent can tell it retrieves Bing-detected crawl errors. However it uses no verb and gives no differentiation from the very similar sibling 'bing_crawl_stats', leaving the agent to guess which of the two is wanted.

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. that the site must be a verified property), and no mention of alternatives such as bing_crawl_stats or bing_url_info. Usage must be entirely inferred 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 behavioral burden, and it discloses nothing: not what statistics are returned, the time window, whether the site must be verified (the schema hints at it but the description does not), or any rate/permission constraints. For a no-annotation tool this is a complete 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?

One short sentence is technically economical, but this is under-specification rather than conciseness; there is no front-loaded verb or scope to orient the agent. Nearly all decision-relevant information is absent.

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?

No output schema and no annotations exist, so the description is the only source of context, and it supplies none about what "crawl statistics" contains or how it differs from bing_crawl_issues. An agent could not confidently choose this tool over its 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 100% and there is a single required parameter (siteUrl) whose schema text explains it is the exact URL of a verified property. Per the high-coverage baseline, the schema does the heavy lifting, so the description adds nothing but does not need to.

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?

"Estadísticas de rastreo de Bing" is essentially a Spanish restatement of the tool name bing_crawl_stats; it names the resource but no specific verb, scope, or metric. It gives no way to distinguish it from close siblings such as bing_crawl_issues or bing_top_queries.

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

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

There is no when-to-use guidance, no prerequisites, and no mention of alternatives, despite a crowded Bing/GSC sibling set. The only usable signal is the tool name itself, so the agent must 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?

With no annotations, the description carries the full behavioral burden, but it discloses nothing about read-only status, authentication requirements, rate limits, or what the returned 'detail' contains. It offers no behavioral context beyond the vague term 'oficial'.

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 concise sentence with no wasted words, and the resource is front-loaded. However, its extreme brevity is not appropriately sized for a tool with no annotations, no output schema, and two required parameters.

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 absence of annotations and an output schema, the description would need to explain return values, usage context, or behavior, but it provides almost nothing. It is too thin to be complete for an agent deciding how to call the tool.

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

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

Schema description coverage is 100%, so the schema fully documents both required parameters (siteUrl, feedUrl). The description adds no meaning beyond what the schema already provides, making 3 the appropriate baseline.

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 is a noun phrase ('Detalle oficial de un sitemap o índice de Bing') that restates the tool name's 'details' without a clear action verb. It identifies the resource domain (sitemap/Bing index) but does not distinguish the tool from siblings like bing_sitemaps or gsc_sitemap_details.

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 guidance is given on when to use this tool versus bing_sitemaps, gsc_sitemap_details, or other sibling tools. There are no prerequisites, exclusions, or alternative routing suggestions.

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 'Lista' does imply a read-only, non-destructive call. It also discloses that verification status is returned, which is useful since there is no output schema. However, it omits auth requirements and any note on scope or result size.

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 waste, appropriately sized for a zero-parameter list tool.

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

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

For a no-argument, no-output-schema listing tool this covers the essential what and includes the returned verification status. Remaining gaps concern auth/scope handling, which are minor for such a simple read.

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 clarify beyond the schema; baseline 4 applies.

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

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

States a specific verb ('Lista') and resource ('los sitios de Bing Webmaster Tools') plus the key returned attribute (verification status). The Bing qualifier implicitly distinguishes it from the Google-side sibling gsc_list_sites, though that contrast is not made explicit.

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 guidance on when to choose this over alternatives such as gsc_list_sites or the other Bing tools, and no prerequisites stated. The agent must infer usage entirely from the description's topic.

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 but discloses nothing beyond the subject matter: no time window, no data-source scope, no auth/permission requirements, no note on whether results are paginated or sampled. For an analytics query tool this is a substantial 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 short, front-loaded sentence with zero waste, but it is under-specified rather than genuinely concise — the brevity costs information an agent needs rather than trimming 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 two-required-parameter query tool with no annotations and no output schema, the description should at minimum clarify the site/page relationship and the meaning of the returned result set. It leaves both 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 100%, so both siteUrl and pageUrl are already documented in the schema (verified property URL, full page URL). The description adds no format or usage nuance beyond that, so the baseline 3 applies.

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

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

The description names the resource (queries) and its relationship to a page in Bing, which is more specific than a tautology, but the verb is absent and the word 'associadas' is ambiguous — it could mean queries that drove clicks, queries the page ranks for, or queries containing the page. Nothing in the text distinguishes it from siblings like bing_top_queries or bing_query_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?

There is no indication of when to use this tool versus alternatives. The sibling bing_query_pages appears to be the inverse mapping (pages for a query), yet the description never states the direction or the conditions that select this tool, leaving routing entirely to inference.

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. It usefully discloses that the output is links rather than data, and that the underlying Bing tools have no public API. However, it says nothing about whether Bing Webmaster Tools authentication is required to follow those links, whether results vary per site, or what the response format looks like beyond 'links'.

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 compact sentence that front-loads what the tool returns before the rationale. No filler, though the purpose and the API caveat are crammed into a single clause rather than separated.

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 one-enum-parameter tool with no output schema and no annotations, the description covers enough: what it returns, the two options, and why it exists instead of an API. The remaining gap (auth requirements for following the links) is minor.

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 'tool' parameter, but its two enum values (robots_tester, site_scan) are self-explanatory and the description names both corresponding tools. Beyond that mapping the description adds no new meaning about the 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 the resource precisely: it returns official links to Bing's Robots.txt Tester and Site Scan tools, which is distinct from the sibling bing_* data endpoints. No verb is used explicitly ('Enlaces oficiales a...'), but the outcome is unambiguous. It lacks any direct naming of sibling alternatives, so it stops short of a 5.

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

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

The clause 'estas herramientas no tienen API pública' implicitly explains why this tool exists and when to reach for it (you cannot fetch this data programmatically), but there is no explicit when-to-use statement, no exclusions, and no guidance on choosing between robots_tester and site_scan. Usage is inferred 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 behavioral burden, and it discloses nothing: no data freshness, no result limits or pagination, no indication of whether it is scoped to a verified property or requires specific auth. 'Bing' implies an external API dependency but no rate limits or failure behavior are mentioned.

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 short sentence with zero padding, which is structurally clean and front-loaded. But it is under-specified rather than concise — the brevity comes at the cost of the information an agent needs.

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 output schema, and only 50% parameter coverage, the description should be doing much more work. It omits return shape, ordering/limits, and the relationship to sibling tools, so the definition is not sufficient 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 coverage is 50%: 'siteUrl' is documented in Spanish as the exact URL of the verified property, but 'query' is undocumented. The description only loosely echoes 'una consulta' without adding format, matching behavior, or syntax beyond what the schema already implies, so it 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 the resource ('páginas') and the scope ('asociadas a una consulta en Bing'), so the agent can infer it returns pages matching a search query. However, it is a bare noun phrase with no verb, and it does not distinguish itself from the very close sibling 'bing_page_queries' (the inverse mapping), leaving the direction of the relationship 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?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as bing_page_queries, bing_top_pages, or bing_backlink_pages. The agent must guess which sibling to call for a pages-by-query question.

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 what is returned (sitemaps and their status), which implies a non-destructive read, but says nothing about pagination, permissions on the verified property, or result 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?

A single compact sentence that front-loads the action and resource with zero filler. Nothing to trim.

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

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

For a simple one-parameter listing tool with no output schema, the description covers the resource and the shape of the return value. Minor gaps remain around pagination and auth expectations, but an agent has enough to call it.

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

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

Schema coverage is 100% with a single, well-documented siteUrl parameter, so the schema does the heavy lifting. The description adds no syntax or format detail beyond what the schema already provides, matching the baseline 3.

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 ("Lista") and resource ("sitemaps enviados a Bing") plus what it returns ("su estado"). The "Bing" scoping implicitly separates it from gsc_sitemaps, but it never names an alternative sibling, so it falls short of full sibling 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?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as gsc_sitemaps or bing_feed_details. The agent must infer the use case purely from the tool 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?

With no annotations, the description carries the full behavioral burden. It discloses one useful trait — a weekly refresh cadence — which implies read-only data, but says nothing about ordering, pagination, limits, or whether the site must be verified. That is thin 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?

Two short sentences with no filler, so nothing is wasteful. However, the brevity reflects under-specification rather than disciplined conciseness — there is simply not enough content to be front-loaded.

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, no output schema, and half its parameters undocumented, the description should explain what is returned, how results are ordered, and the role of limit. It omits all of that and is also in a different language from the schema and sibling tools, adding friction for selection.

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

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

Schema coverage is only 50%: siteUrl is documented as the verified property URL, but the limit parameter (default 100, max 1000) is undocumented in both schema and description. The description adds no parameter meaning at all, so it 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?

"Páginas principales de Bing" names the resource and implies a ranked list of top pages, but supplies no verb and no scope qualifiers (time window, ranking metric, per-site vs. global). Among siblings like bing_page_queries and bing_top_queries, an agent cannot tell from the description alone which resource this returns or how it differs.

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

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

The description gives no when-to-use guidance, no prerequisites, and no named alternatives among the many Bing/GSC siblings. The only extra information, that the source refreshes weekly, is a data-freshness note rather than usage 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 behavioral burden and largely fails to. It does disclose one useful trait — the data refreshes weekly — but says nothing about read-only nature, permissions/auth requirements, or result scope for what is clearly a data-retrieval 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?

Two short, front-loaded sentences with zero filler. It is efficient, though the brevity borders on under-specification rather than deliberate trimming.

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 retrieval tool with a required siteUrl, an undocumented limit, no output schema, and no annotations, the description is far too sparse. An agent still cannot tell what a returned 'top query' contains or how limit affects results.

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

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

Schema coverage is only 50%: siteUrl is documented ('URL exacta de la propiedad verificada') while limit is entirely undocumented in both schema and description. The description adds nothing about parameter meaning or format, so it does not compensate for the 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 identifies the resource (top queries) and the source (Bing), which tells an agent broadly what it retrieves. However, it is a bare noun phrase with no verb and no differentiation from close siblings like bing_top_pages, bing_page_queries, or bing_query_pages, so what exactly a 'top query' is (search terms for the property?) is left implicit.

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 indication of when to use this tool versus the many Bing siblings, no prerequisites, and no exclusions. The agent is given no routing guidance 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?

No annotations are provided, so the description carries full behavioral burden. It implies a read-only informational lookup via 'Información', but does not disclose permissions, rate limits, whether the site must be verified, response behavior, or any other operational trait.

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 or repetition. It is appropriately sized for a brief tool description, even if additional details are missing elsewhere.

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 simple two-parameter lookup with complete schema descriptions, the description is minimally sufficient to identify the tool's subject. However, with no annotations and no output schema, it omits return-value expectations and usage context that would help an agent 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 100%, and both required parameters are documented in the schema. The description adds no parameter-level meaning beyond what the schema already provides, so the baseline of 3 applies.

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

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

States the specific resource (una URL) and the domain/source (API de Bing) for crawl and indexing information. It is clear what the tool returns, but it does not explicitly distinguish itself from similar siblings such as gsc_inspect_url or bing_crawl_issues.

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

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

The description gives no when-to-use guidance, no alternatives, and no prerequisites beyond referencing the Bing API. An agent must infer that this is the Bing URL-inspection tool rather than one of the many sibling Bing/GSC 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 operation but discloses nothing about what the summary contains, whether it requires a prior local import, permissions, or freshness/state behavior — significant gaps for an unannotated 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?

It is a single efficient sentence with no padding, which is good, but its brevity comes at the cost of clarity rather than achieved through sharpening — it is under-specified rather than genuinely concise.

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

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

With no annotations, no output schema, and an opaque single-line description, the definition leaves too much unsaid for an agent to call it confidently. It never explains what constitutes the 'generative CSV' or what the returned summary includes.

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

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

Schema coverage is 100% and the single siteUrl parameter is fully documented in the schema. The description adds no meaning beyond it, so the baseline of 3 applies.

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

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

It states it returns a summary of a locally imported generative Google CSV, which is a specific resource, but the phrasing is opaque ('CSV generativo de Google importado localmente') and never names a clear action verb. An agent can roughly tell it apart from the gsc_*/bing_* siblings only by the 'geo_report' prefix.

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 and no named alternative among the many gsc_/bing_ tools. The words 'importado localmente' hint at a prerequisite (a prior local import must exist) but this is left implicit 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?

With no annotations, the description carries the full behavioral burden. It discloses one real trait beyond the schema — Bing's ingestion lag for new sites — and implicitly confirms a read operation via the get_ name, but it omits permissions/auth needs, any rate-limit behavior, and the return shape.

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

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

Two short sentences, zero filler, with the scope statement front-loaded before the latency caveat. It is efficient, though the first sentence is generic enough that the key metric names are absent.

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 three-required-parameter read tool with no annotations and no output schema, the description should convey what comes back and how it is scoped. It conveys the date-range semantics and a latency note but says nothing about the returned metric set, leaving the agent to infer return values from the name.

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

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

Schema coverage is 100%, so the baseline is 3, but "rango inclusivo" adds a semantic the schema does not: the schema only says "Fecha YYYY-MM-DD" for startDate/endDate, leaving inclusivity ambiguous, whereas the description pins down that both bounds are included.

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?

"Métricas diarias de Bing" states a resource and cadence, and "rango inclusivo" scopes the query, but the description never names the metrics (clicks and impressions) that the tool actually returns — that only appears in the tool name. It does not distinguish this daily-metrics tool from siblings like bing_top_queries or bing_top_pages, so the agent must infer the boundary.

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 tool versus the many bing_* alternatives, nor any prerequisite (e.g. properties must be verified before calling). The only guidance — that Bing may be slow to have data for new sites — is a data-freshness caveat, not usage 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 usefully discloses that it reads Google's stored record and does not perform a live test, implying a non-mutating read. However, it omits quota/rate-limit behavior and any permissions or site-verification requirements that are material for the URL Inspection surface.

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

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

A single front-loaded sentence that states the action, the subject, and the key scope limitation with zero filler. Every clause earns its place, with the negative constraint placed last as a qualifier.

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 and no output schema, the description is the only behavioral source, and for a two-required-param read tool it covers the core purpose adequately. It nonetheless leaves gaps: the returned index-status fields and the constraint that url must belong to the verified siteUrl property are not addressed.

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

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

Schema description coverage is 100%, and both parameters (url, siteUrl) are documented in the schema itself, so the baseline is 3. The description adds no meaning about the relationship between the two required parameters or the format constraints beyond what the schema already states.

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: checking Google's recorded index status for a URL. It also clarifies what it is not ('no ejecuta una prueba en vivo'), which helps distinguish it from a live-test capability. It stops short of naming any sibling tool (e.g. gsc_page_performance, bing_url_info) as the alternative.

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 clause 'no ejecuta una prueba en vivo' implies when this tool applies (retrieving stored index state rather than triggering a fresh crawl), but it never states explicit when-to-use or when-not-to-use conditions versus the many sibling reporting tools. Usage is left to inference.

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 entire behavioral burden, yet it discloses nothing beyond the bare operation. It does not say whether the list is scoped to the authenticated user's permissions, whether OAuth/credentials are required, whether results are paginated, or what a returned property looks like.

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. For a zero-argument listing tool this is an appropriately sized description.

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 output schema and no parameters, the description is the only source of information, and it omits what the call actually returns (property identifiers, permission levels, format) and any auth context. Adequate to identify the operation but not complete for calling 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?

The tool takes zero parameters, so the baseline of 4 applies; there is nothing for the description to disambiguate. The description correctly implies no filtering or input is needed.

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 ('Lista') and resource ('propiedades accesibles en Google Search Console'), which is enough to separate it from bing_list_sites by data source. It never explicitly names that sibling or scopes what a 'propiedad' contains, so it stops short of a fully discriminating 5.

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

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

Usage is only implied: as a listing call it is the natural discovery step before gsc_search_performance, gsc_sitemaps or gsc_inspect_url, but the description says nothing about when to prefer it over bing_list_sites or that it should be called first. No exclusions or prerequisites 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, the description carries the full behavioral burden. It does disclose one genuinely useful trait — that results are heuristics, not official errors — which calibrates the agent's trust in the output. But it omits whether the tool is read-only, what happens with unverified siteUrl, date-range limits, and the effect of the minImpressions/limit thresholds on results.

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 sentence with the detection criteria front-loaded and no filler; the heuristic caveat is attached efficiently at the end. It is appropriately sized, though the criteria and the caveat could be split for faster 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?

No output schema and no annotations, yet the description does not explain the return shape (ranked list? fields per query?), the meaning of limit, or any pagination. For a 5-parameter heuristic-detection tool, the conceptual framing is present but the operational details an agent needs are 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 coverage is 60%: siteUrl and both dates are documented in-schema, but minImpressions and limit are not described anywhere. The description mentions CTR and position thresholds but never ties these to parameters, so it does not compensate for the coverage gap. Baseline 3 is appropriate.

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

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

The description names a concrete resource (queries) and the exact detection criteria — low CTR in top 10, or average position between 10 and 20 — plus a framing note that these are heuristics. It is specific enough to predict the output, but it never differentiates itself from close siblings like gsc_query_advanced or gsc_search_performance, and it lacks an explicit verb such as 'list' or 'detect'.

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 phrase 'conviene investigar' implies the usage context (SEO opportunity triage), so the intent is inferable. However, there is no explicit when-to-use statement, no exclusion criteria, and no pointer to the sibling tools (gsc_query_advanced, gsc_page_performance) that overlap in scope. Guidance is implied, not 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 disclosure burden, yet it says nothing about authentication against the verified property, row limits, date-range constraints, or result volume. It does imply the shape of the output (daily series plus top queries), which is the only behavioral hint present.

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; every clause carries content. It is appropriately sized, though it is too terse to be exemplary.

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 and no output schema, the description should carry more weight, but the fully documented input schema offsets the parameter gap. It hints at return contents without specifying date-range limits or result structure.

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

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

Schema description coverage is 100% and all four parameters are documented in the schema with format and pattern detail, so the baseline is 3. The description adds only the notion that the url must be an exact page, which the schema already conveys.

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

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

The description names a specific resource (una página exacta) and the data returned (serie diaria y consultas principales) inside Google Search Console, so an agent knows exactly what it fetches. It does not, however, explicitly distinguish itself from siblings like gsc_search_performance or gsc_query_advanced.

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

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

There is no when-to-use guidance, no prerequisites and no mention of the alternative tools for site-wide or query-level reporting. The only signal is the implicit inference that this is the per-page variant.

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 supplied, so the description carries the full burden, and it does disclose one genuine behavioral trait: Google may cap/limit returned rows, which directly motivates pagination. It omits other important behavior such as auth requirements (verified property), rate limits, default row counts, and how multiple filters are combined.

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 waste and no boilerplate. It is efficient, though arguably too terse for an 8-parameter tool, which is a completeness issue rather than a structural one.

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 an 8-parameter tool with no annotations and no output schema, one sentence is thin. Filter combination logic, defaults for limit/startRow, and the shape/meaning of the response are all unaddressed, leaving real gaps 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 only 38% across 8 parameters. The description compensates partially by mapping to dimensions (1-3), filters, and pagination, but says nothing about type, siteUrl, or date handling, leaving several parameters undocumented in both places.

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

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

The description names the resource and the actual capabilities (Search Analytics query with 1-3 dimensions, filters, pagination), so an agent knows this is the raw/flexible query tool. It does not, however, contrast itself with siblings like gsc_search_performance or gsc_page_performance, so the agent must infer that this is the general-purpose variant.

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 and no mention of alternatives. The row-limit note hints that pagination (startRow/limit) may be needed, but the description never says when to pick this over the fixed-report 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?

With no annotations, the description carries the full burden and falls short: it says nothing about authentication/verified-property requirements, rate limits, how the dimension choice changes aggregation, or whether the default limit caps results at 1000 rows. Only the phrase 'Google Search Console' hints at the data source.

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 listing metrics first and breakdowns second, with no filler. It is efficient, though the fragmentary noun-phrase style leaves the action verb implicit.

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

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

With no output schema, the description must convey return shape; it does name the metrics, which is helpful, but omits pagination/limit behavior, date-range semantics, and auth requirements. It is minimally adequate rather than complete for a 5-parameter analytics tool.

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

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

Schema description coverage is 60%, and the description restates the dimension values (date, query, page, country, device) that the enum already lists, adding little beyond the schema. It offers no guidance on the 1000-row limit or the interaction between dimension and returned shape.

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?

It names the specific resource (Google Search Console performance data) and enumerates the metrics returned (clicks, impressions, CTR, position) plus the available breakdowns, so an agent knows what data it yields. It does not, however, distinguish itself from close siblings like gsc_page_performance or gsc_query_advanced, which appear to overlap.

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

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

There is no when-to-use guidance, no mention of prerequisites (a verified property is required), and no routing to alternatives such as gsc_page_performance or gsc_query_advanced. The only hint of context is the enumeration of dimensions, which the enum already supplies.

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 read-only nature, required permissions, error behavior when the sitemap is not found, or what 'oficial' data is returned. It only implies that data comes from Search Console, which is minimal.

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 with no wasted clauses, so it is structurally clean and front-loaded. But it is under-specified rather than concise: the word 'oficial' contributes little, and the sentence is too thin to be genuinely useful.

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 read tool with no annotations and no output schema, the description never explains what detail is actually returned or under what conditions the call fails. The schema covers the inputs, but the output and edge cases are left entirely 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 100% and both parameters (siteUrl, sitemapUrl) are documented in the schema, so baseline 3 applies. The description adds no extra meaning about the parameter format or how the two URLs relate, merely repeating the sitemap concept.

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 phrase 'Detalle oficial de un sitemap enviado a Search Console' names a specific resource (a sitemap) and its scope (one submitted to Search Console), which is far more precise than a tautology. However it uses a noun phrase with no verb and never differentiates itself from the sibling gsc_sitemaps (listing) tool, so an agent must infer that this returns a single sitemap's detail rather than a collection.

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 preconditions (e.g. the site must be verified, the sitemap must already be submitted), and no reference to any alternative such as gsc_sitemaps. The agent receives no routing signal 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?

No annotations are provided, so the description carries the full disclosure burden. 'Lista' implies a non-destructive read, which is the key behavioral trait here, but the description says nothing about auth requirements, pagination, or whether results are scoped to the verified property. Adequate for a trivial read but leaves 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?

A single efficient sentence with the action front-loaded and no wasted words. It is appropriately sized, though it borders on being too terse for the information an agent might want.

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 one-parameter, read-only list operation with a fully documented schema and no output schema, the description is minimally sufficient. It omits any hint of what the response contains (sitemap URLs, statuses, last-download times), which would help an agent decide whether this tool answers its question.

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

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

Schema description coverage is 100% and there is only one parameter (siteUrl), whose schema description already explains it is the exact URL of the verified property. The description's phrase 'de una propiedad' merely restates that, adding no new format or constraint detail. Baseline 3 applies.

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

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

States a clear verb+resource: 'Lista los sitemaps de una propiedad de Google Search Console.' An agent can distinguish this from bing_sitemaps by the GSC scope. It does not, however, differentiate itself from its close sibling gsc_sitemap_details, which would fetch detail for a single sitemap.

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. a verified GSC property), and no routing to alternatives such as gsc_sitemap_details or gsc_list_sites. The agent must infer usage entirely from the name and description.

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 little: 'rastreo acotado' hints at bounded crawling and 'APIs oficiales' implies external API calls, but there is no mention of auth/verification requirements for the GSC/Bing properties, rate limits, runtime, cost, or what the 'plan de acción con evidencia' actually contains.

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 clause that front-loads the core capability and enumerates its three components; every word earns its place. It is concise but so terse that brevity shades into under-specification.

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 six-parameter, multi-source audit tool with no annotations and no output schema, the description is far too thin: it omits the prerequisites (verified GSC/Bing properties), the crawl bound semantics, and any hint of what is returned, so an agent cannot confidently invoke it.

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

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

Schema description coverage is 83% (above the 80% baseline), so the schema already documents baseUrl, dates, and site URLs. The description adds no parameter-level meaning (it does not explain maxPages, the date window's effect, or the distinction between baseUrl and gscSiteUrl/bingSiteUrl), so baseline 3 applies.

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

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

States a clear verb+resource: an advanced SEO and GEO audit that uses official APIs, bounded crawling, and produces an action plan with evidence. The scope is intelligible, but it never distinguishes itself from the sibling seo_audit_site, leaving the agent unable to tell the two audits apart.

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 reference to the obvious alternative seo_audit_site (nor to the many bing_*/gsc_* siblings) even though the tool name is nearly identical to a sibling. The agent must infer selection entirely on its own.

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 it does disclose two real traits: results are evidence-backed and 'errores parciales' (partial errors) are tolerated rather than fatal. It does not state that this is a read-only aggregation, what permissions/properties are required, or how many sources must be available for the audit to run.

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

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

A single dense sentence with no filler; the output characteristics are front-loaded ahead of the error-tolerance note. It is efficient, though it leans on a noun phrase rather than a leading action verb, which slightly weakens 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?

For a composite audit tool with five parameters and no output schema, the description covers the return shape at a high level (evidence, prioritized findings, partial errors) but says nothing about scope, which sources are mandatory, or how results differ from seo_audit_advanced. Adequate but with clear 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 coverage is 100%, so all five parameters (url, startDate, endDate, gscSiteUrl, bingSiteUrl) are already documented in the schema. The description adds nothing about defaults, precedence between url and the site-URL fields, or the date-range semantics, so the baseline 3 applies.

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

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

The description names the resource ('Bing y/o Search Console') and the output shape ('auditoría resumida ... con evidencia, hallazgos priorizados'), so an agent can tell it produces a summarized audit. However, it omits an explicit verb (does it generate, run, or return the audit?) and never names 'seo_audit_advanced', its closest sibling, so the boundary between the two 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 guidance on when to pick this tool over the ~20 sibling tools, in particular seo_audit_advanced or the individual bing_*/gsc_* tools. The 'y/o' phrasing hints that either Bing or GSC may be selected, but no condition, prerequisite, or exclusion is stated.

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