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

With no annotations, the description carries the full burden. It does disclose one meaningful post-condition (verification is required after adding), which is real behavioral context. However, it omits idempotency behavior, required auth level, and the outcome when the site already exists.

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 zero filler; the core action is front-loaded and the verification caveat follows 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 explained. For a mutation tool with no annotations, though, the description is thin: it does not cover permissions, duplicate-handling, or what verification entails, which are the main things an agent would need.

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

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

There is a single parameter with 100% schema description coverage, so the schema already defines site_url as the property identifier. The description adds no format guidance (e.g. URL vs domain property syntax), 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?

The description states a specific verb and resource ("Add a property to Search Console"), which clearly distinguishes it from siblings like delete_site and list_sites. It stops short of naming an alternative or contrast condition, but the action is unambiguous.

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

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

Usage is implied by the verb and the note that verification is required afterwards, but the description never states when to add a site versus other management tools, nor any prerequisites (permissions, ownership) or what to do if the property already exists.

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 reasonably well: it discloses what the check exposes (credential resolution, read-only mode, OAuth scopes), which is meaningful behavior beyond the empty schema. It stops short of saying whether this performs a live network round-trip or how failures 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?

One-sentence purpose followed by a compact 'Returns' block; the key claim (configured and can authenticate) is front-loaded and 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?

The description is adequate for a simple zero-param diagnostic, and the 'Returns' section redundantly but harmlessly previews the output schema. It lacks only guidance on interpreting failure (e.g., what a false credential resolution implies for subsequent calls).

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

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

The tool takes zero parameters, so the baseline is 4 by rule. The description correctly signals a no-input check and adds no misleading parameter expectations.

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 ('check') and resource (the Search Console client's configuration/authentication), which unambiguously separates it from the data-fetching siblings like list_sites and query_search_analytics. An agent can tell this is a diagnostic/preflight tool without opening the 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?

Usage is only implied: the purpose (verify config and auth) suggests calling it before other operations or when auth fails, but the description never states when to use it, when not to, or what to do with the result. No alternatives are named.

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 disclose whether the operation is read-only, what permissions are required, whether there are rate limits, or how pagination works.

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 zero waste. The comparison semantics are stated 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?

The schema fully documents parameters and an output schema exists, so the description need not cover returns. Still, it omits when-to-use guidance and behavioral context, leaving it only minimally complete for an analytics comparison 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 parameter meanings are already fully documented in the schema. The description adds no parameter-level meaning beyond what is structured.

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: compare a period against the equal-length period immediately before it. However, it does not distinguish this tool from sibling analytics tools such as performance_by_date or query_search_analytics.

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 alternatives are given. The description only says what the tool does, leaving the agent to infer when it should be selected over 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 provided, the description carries the full burden and succeeds in disclosing key behavior: the property is unlinked from the account, and historical data remains with Google but is inaccessible until re-adding and re-verification. It does not mention permission requirements or confirmation behavior, which keeps it from a 5.

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

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

Two sentences, front-loaded with the core action and immediately followed by the key consequence. Every sentence earns its place with no 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?

The tool has one required parameter with full schema coverage and an output schema that handles return values. The description fully covers the effect and data-retention behavior, leaving nothing essential for an agent 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 100%, so the single site_url parameter is already well documented. The description adds no further syntax or format details beyond what the schema provides, matching the baseline for full schema coverage.

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

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

The description names a specific verb and resource: 'Remove a property from Search Console.' It clearly distinguishes this tool from sibling operations like add_site and delete_sitemap, which target different resources.

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

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

The description implies when to use the tool by saying it removes a property, but it does not explicitly state when to choose this over alternatives such as delete_sitemap or list_sites. 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?

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing beyond the bare action. It does not state that deletion is irreversible, whether the sitemap must first exist, whether the property permission level matters, or what happens on a nonexistent sitemap. For an unannotated destructive mutation 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 short sentence with zero filler, and the action verb is front-loaded. Nothing is padded or repeated.

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 the description is still incomplete for a destructive, unannotated tool. It should at minimum state irreversibility and any preconditions for deletion; as written, the agent learns nothing it could not already infer from the tool name and schema.

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

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

Schema description coverage is 100%; both site_url (property identifier) and feedpath (full URL of the sitemap) are documented in the schema itself. The description adds no syntax, format, or example detail beyond that, 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?

The description states a specific verb (Delete) and resource (a sitemap from Search Console), so an agent can immediately tell what the tool does. However, it makes no attempt to distinguish itself from siblings such as submit_sitemap, submit_sitemaps, or get_sitemap, so differentiation 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 use this tool versus alternatives, no precondition stating the sitemap must already be registered, and no mention of authorization requirements. The agent must infer that this is the inverse of submit_sitemap 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 discloses that the response includes the caller's permission level and implies a read-only operation, but does not state auth requirements, explicitly confirm read-only behavior, or describe error handling.

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 word contributes to stating the verb, resource, and additional return 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?

Given the low complexity (one fully documented parameter), the presence of an output schema, and no annotations, the description is nearly complete. It could be improved by clarifying when to choose get_site over list_sites, but it provides enough to invoke the tool correctly.

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

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

Schema description coverage is 100%, so the sole parameter 'site_url' is already fully documented in the schema. The description adds no additional meaning, syntax, or constraints beyond what the schema provides; 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?

States a specific verb ('Get') and resource ('Search Console property'), plus an additional return item ('caller's permission level'). It implicitly distinguishes from list_sites by saying 'one', but does not explicitly name or contrast with any sibling tool.

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 use this tool versus list_sites or other siblings. It does not state prerequisites, exclusions, or alternatives, leaving the agent to infer usage from the purpose 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 burden. 'Get' plus the read-oriented framing (status and error counts) makes the read-only, non-destructive nature apparent, but permissions, whether an unsubmitted or unprocessed sitemap returns an error, and rate-limit behavior are all undisclosed.

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 the resource and the returned content front-loaded. No filler, no restatement of the title.

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 need not explain return values, and the two parameters are fully documented in the schema. For a simple single-resource read this is nearly complete; only the usage routing against list_sitemaps/submit_sitemap siblings is missing.

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

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

Schema description coverage is 100%: feedpath is documented as a full URL with an example and site_url as a property identifier. The description adds no further parameter meaning, so the baseline 3 applies.

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

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

States a specific verb (Get) and resource (one sitemap), plus what it returns: processing status and error counts. It implicitly distinguishes itself from the plural sibling list_sitemaps, though it never names that sibling or explicitly contrasts the two.

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: an agent can infer this is for inspecting a single already-known sitemap rather than enumerating them, but the description gives no explicit when-to-use condition, no prerequisite (e.g. the sitemap must have been submitted), and no named alternative such as list_sitemaps.

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. 'Inspect' implies a read-only, non-destructive operation, and the output schema covers return values, but the description does not disclose permission requirements, quota behavior, or Search Console property ownership 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?

A single efficient sentence front-loads the operation and resource. There is no redundant or wasted phrasing.

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 read-only inspection tool with full schema descriptions and an output schema, the description is largely complete: it identifies the operation, scope, and resource. It could explicitly route the agent to 'inspect_urls' for multiple URLs, but that is the main missing contextual detail.

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 input schema already documents all three parameters clearly. The description adds only the concept of inspecting one URL's index status and does not contribute additional parameter syntax or constraints beyond the schema.

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

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

States a specific verb ('Inspect'), a clear resource ('one URL's index status in Google Search'), and the singular scope distinguishes it from the sibling 'inspect_urls' bulk tool. An agent can identify the operation without opening the 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?

The phrase 'one URL' implies this is for single-URL inspection versus the plural sibling 'inspect_urls', but the description does not explicitly say when to use this tool, when not to, or that batch inspection should use the alternative. Usage is only implied.

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 usefully discloses a hard operational constraint: one unit per URL against a 2,000-per-property-per-day quota. It says nothing about auth requirements or partial-failure behavior across multiple URLs, which is the main remaining gap.

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

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

Two short sentences, front-loaded with the action and result, then the cost constraint. Every sentence earns its place with 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, and all parameters are schema-documented. The quota disclosure fills the biggest behavioral gap; only the missing routing guidance versus inspect_url keeps this from being 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 100%, so all three parameters (site_url, language_code, inspection_urls) are already documented in the schema. The description adds no syntax, format, or constraint detail beyond that, so the baseline 3 applies.

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

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

The description gives a specific verb and resource ('Inspect several URLs') plus the purpose of the result ('summarise their index status'). The plural framing implicitly distinguishes it from the singular sibling inspect_url, but it never names that sibling explicitly, so differentiation relies on 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?

Apart from the quota cost note, there is no guidance on when to choose this over inspect_url or the other sibling tools, and no stated prerequisites or exclusions. The agent must infer that this is the batch counterpart to inspect_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 full behavioral burden, and it says nothing about read-only vs mutating semantics, permissions/auth, pagination, or limits. A single sentence for a bare list operation leaves the agent with little beyond the read-only inference from the verb 'List'.

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 wasted words and the key scope ('submitted for a property') front-loaded. It is efficient, though arguably under-specified rather than tight for a tool with siblings needing differentiation.

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 core read operation is conveyed. But with no annotations and no usage or behavioral context, the definition is only minimally complete for selecting this tool among its many 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%, including a well-documented sitemap_index parameter explaining child-sitemap listing, so the schema does the heavy lifting. The description adds no parameter meaning beyond what is already documented, which matches the baseline 3 for high 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 gives a specific verb (List) and resource (sitemaps) scoped to a property, which is clearer than the title alone. However, it does nothing to distinguish itself from close siblings like get_sitemap, submit_sitemaps, or delete_sitemap, so an agent must infer the difference from names 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?

There is no statement of when to use this tool versus alternatives, nor any prerequisites or exclusions. The agent must guess, for example, that this lists sitemaps while get_sitemap retrieves a single one.

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 implicitly conveys a safe read-only enumeration and names the returned fields, but says nothing about permissions needed or result limits; the return details are also partially redundant given an output schema exists.

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, front-loaded with the core action and scope, followed by a compact return summary. Every line earns its place with 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?

For a zero-parameter list tool with an output schema, the description covers what it does and what comes back, so an agent can call it confidently. The only shortfall is the absence of any usage context or sibling routing.

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

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

The tool takes zero parameters, which is the documented baseline of 4. There is no parameter meaning for the description to add, and it correctly avoids inventing any.

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 ('List all Search Console properties') with an explicit scope ('the account can access'). It is clearly distinguishable from siblings like get_site, add_site, and delete_site, though it does not name any of 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?

Usage is only implied: an agent can infer this is the discovery step before using get_site/add_site, but the description offers no when-to-use framing, prerequisites, or explicit alternatives. Adequate but with clear gaps.

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, and it adds nothing: no mention of default date windowing, row-limit behavior, rate limits, or authentication needs. The schema does encode defaults (28-day window, row_limit 100), but the description offers no behavioral context beyond the title.

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 no filler and the grouping dimension front-loaded. It is efficient, though its brevity borders on under-specification rather than tight writing.

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, and the schema covers parameters well. Still, for a tool in a family of four 'performance_by_*' siblings with no annotations, the description should at minimum say what metrics are reported and how it differs from the other breakdowns.

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%, including enum values, defaults, and the date-window default, so the schema fully documents all six parameters. The description adds no additional parameter meaning, which is the expected baseline when the schema does the heavy lifting.

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

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

The phrase 'Performance broken down by country' names the resource and the grouping dimension, which loosely distinguishes it from siblings like performance_by_date. However, 'performance' is never defined (clicks, impressions, CTR, position?), so the purpose is only implied rather than stated with a concrete verb/resource pair.

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 performance_by_date, performance_by_device, or performance_by_search_appearance, nor any mention of prerequisites such as which site properties are valid. The agent must infer usage 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?

No annotations are provided, so the description carries the full burden, yet it only restates the shape of the result. It says nothing about read-only behavior, authentication/scope requirements, rate limits, data freshness, or the default 28-day window semantics that drive 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 eight-word sentence with no filler and a front-loaded subject. It is efficiently sized, though arguably too terse to carry any detail an agent could use.

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 schema covers all six parameters. However, given the dense sibling set of similar performance_* tools and the absence of annotations, the description omits any disambiguation or behavioral context needed to pick this tool 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 coverage is 100%, so every parameter (including filter combination semantics, inclusive date bounds, row_limit, and the search_type enum) is already documented in the schema. The description adds no syntax, format, or interaction detail beyond that, 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 a specific resource (performance) and a specific dimension (daily/date-based time series), which implicitly distinguishes it from the sibling dims performance_by_country and performance_by_device. It does not explicitly name an alternative, so it falls 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 when-to-use guidance, no mention of when to prefer it over performance_by_country/performance_by_device or query_search_analytics, and no prerequisites. The reader must infer intended usage from the name 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 behavioral disclosure burden. It does not state read-only/destructive status, authorization needs, rate limits, or that it returns aggregate reporting rather than modifying data; only the tool name implies a 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?

A single front-loaded sentence with no wasted words. It is extremely terse, but conciseness is appropriate and not verbose.

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 and the input schema fully documents parameters, so the description need not explain return values or parameter details. It identifies the device breakdown clearly enough to route among the performance_by_* siblings, though it omits usage and behavioral 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 100%, so the schema already documents all five parameters including defaults and the search_type enum. The description adds device breakdown context but no parameter semantics beyond what the schema provides; baseline 3 applies.

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

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

States a specific resource and breakdown dimension ('performance broken down by device'), and 'by device' distinguishes it from siblings like performance_by_date, performance_by_country, and performance_by_search_appearance. However, it lacks an explicit verb and does not directly name 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?

Provides no when-to-use guidance, prerequisites, or comparison to alternative performance breakdown tools. The agent is not told when to choose this over performance_by_date, performance_by_country, or compare_periods.

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 usefully discloses a request-level limitation (the dimension cannot be combined, hence no filters argument), which is genuine behavioral context. However, it says nothing about read-only nature, permission scope, pagination, or result ordering.

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

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

Two sentences, front-loaded with the core purpose and followed by the single most surprising design fact. No filler, no restatement of the title.

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, and the schema fully documents parameters. The description supplies the one non-obvious constraint about dimension incompatibility. Minor gaps remain around result ordering and how appearance types are enumerated, but nothing blocking.

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 end_date, site_url, row_limit, start_date and search_type are all documented in the schema itself. The description adds no parameter-level detail beyond explaining the deliberate absence of a filters argument, so the baseline 3 applies.

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

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

States a specific verb and resource ('Performance broken down by search appearance') and clarifies the dimension with 'rich result types'. The dimension name inherently distinguishes it from parallel siblings like performance_by_date, performance_by_country and performance_by_device, though it never names them 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?

The note that SEARCH_APPEARANCE cannot be combined with other dimensions gives a real usage constraint, but there is no explicit statement of when to pick this tool over the parallel performance_by_* siblings or what the intended scenarios are. Usage is only implied by the groupby dimension.

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 pagination behavior past the 25,000-row cap, which is genuinely useful, but adds nothing about rate limits, permission requirements, or the cost of exhaustively paging large result sets despite max_rows defaulting to 100,000.

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, front-loaded with the action and the distinguishing pagination behavior. Every word earns its place with no redundancy.

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

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

The description covers the core purpose and the row-cap behavior, and an output schema exists so return values need not be explained. However, for an 8-parameter exhaustive-retrieval tool with no annotations, the lack of guidance on cost, permissions, or when to prefer it over narrower analytics siblings leaves meaningful 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 100%, so the schema already documents all 8 parameters including enums, defaults, and date formats. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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

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

States a specific verb (retrieve) and resource (every row for a query) and distinguishes itself by promising full retrieval past the 25,000-row cap, which sets it apart from siblings like top_queries that likely cap results. It doesn't explicitly name which sibling to use instead, keeping it from 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?

No explicit when-to-use or when-not-to-use guidance relative to the many analytics siblings (query_search_analytics, top_queries, performance_by_date). The agent must infer that this is the exhaustive-retrieval option from the phrase 'every row,' with no stated exclusions or cost warnings.

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 the query is 'raw' and 'full control', but says nothing about authorization requirements, rate limits, whether results are paginated (though the schema mentions paging), or what the return structure is (output schema exists, so that's partially covered). For a complex 10-parameter analytics tool with 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?

Ten words in the first sentence and a single list of alternatives in the second — no filler, and the key distinction (raw vs. preset) is 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?

Given the 10 parameters and no annotations, the description does not provide enough operational context (e.g., auth scope, rate limits, pagination behavior beyond what the schema implies). An output schema exists so return-value explanation is not required, but behavioral gaps remain for a complex query 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 already documents all 10 parameters depthfully. The description adds no parameter-level meaning beyond the schema. Baseline 3 is appropriate when the schema is comprehensive.

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 states a specific verb and resource ('Run a raw Search Analytics query') and the second sentence clarifies the tool's positioning ('unmodified API method'). However, it doesn't explicitly state what distinguishes it from the named siblings beyond being raw/not preset; the mechanism of distinction is implied by the alternative names.

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 names seven alternative tools for common cases (top_queries, top_pages, performance_by_date, etc.) and states the condition for using this tool ('full control over the request'), creating a clear when-to-use / when-to-use-something-else split.

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 does so well: it discloses the API shutdown date, that calling it returns an error, and that it exists only for API-surface completeness. It stops short of describing the concrete error shape or whether the call still consumes quota, but the essential behavior is unambiguous.

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 critical warning is front-loaded in the first line, followed by the reason and the alternative. Every sentence earns its place and 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 return values need no explanation. Combined with the deprecation status, error behavior, and the explicit redirect to inspect_url, an agent has everything needed to decide not to call this 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% and both parameters (url, request_screenshot) are documented in the schema, so the baseline is 3. The description adds nothing about parameter semantics, but the schema already does the heavy lifting for a two-param tool.

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 verb+resource ('Run the Mobile-Friendly Test on a URL') and immediately qualifies it with 'DEPRECATED AND NON-FUNCTIONAL', so an agent understands both the nominal purpose and its unusability. It also names a sibling (inspect_url) so it can be distinguished without opening schemas.

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

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

Explicitly says 'Do not call it expecting a result' and redirects to the alternative ('use inspect_url instead, whose response carries a mobileUsabilityResult'), naming the exact field to look for. This is textbook when-not-to-use plus the replacement path.

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 says nothing about idempotency, permissions, error handling, rate limits, or what happens if the sitemap is invalid — only that a submission occurs.

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. It is structurally sound but extremely terse for a mutation 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?

An output schema exists, so return values need not be explained, and the input schema is fully described. However, the description lacks sibling differentiation and behavioral context for a write operation, leaving it partially incomplete.

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

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

Schema description coverage is 100%, so the schema already documents both parameters. The description adds no additional meaning about site_url or feedpath formats beyond what the schema provides, making the baseline of 3 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?

States a specific verb 'Submit' and resource 'sitemap' with the destination 'Search Console,' making the core action clear. However, it does not distinguish this tool from the sibling 'submit_sitemaps,' leaving ambiguity for an agent choosing between the two.

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 mention of alternatives like submit_sitemaps, and no prerequisites or conditions for invocation. Usage is only implied by the verb.

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 doesn't disclose what happens on duplicate or invalid URLs, whether re-submission is idempotent, any per-property sitemap limits, or auth requirements for a mutating submission.

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 batch scope and target are stated 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?

With an output schema present and full parameter coverage, return values need no explanation. However, for a mutating submission tool with zero annotations and a near-identical sibling, the description leaves behavioral expectations and tool selection entirely to inference.

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 site_url and feedpaths are already documented as a property identifier and a list of full sitemap URLs. The description adds only the constraint that all submitted sitemaps target one property, which is marginal over the schema.

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

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

The description gives a specific verb (Submit) and resource (sitemaps) plus the batch scope ('several sitemaps... in a single call'), which implicitly distinguishes it from the singular submit_sitemap sibling. It stops short of naming that alternative, so differentiation is inferable 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?

'Several sitemaps ... in a single call' hints at the batch use case versus the singular submit_sitemap, but the description never explicitly says when to use this tool instead of that sibling or what preconditions (ownership/verification of the property) apply. Usage 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 behavioral burden, and it discloses almost nothing: not that this is a read-only, non-destructive query, not how ranking is defined (implicitly clicks descending?), and not pagination or row_limit truncation behavior. For a multi-parameter analytics 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, which is structurally efficient. It is arguably under-specified rather than concise, but it wastes no 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 restated, but with six parameters, no annotations, and a ranking-based semantic, the description leaves the agent without ordering rules, default behavior context, or safety profile. Too thin for a core analytics query 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 already documents site_url, filters, dates, row_limit, and search_type, making 3 the baseline. The description adds nothing beyond the schema, not even clarifying that 'top' is ranked by the click metric the schema never names.

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

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

States a specific resource (landing pages), a metric (clicks), and a scope (a property), which is enough to place it among siblings like top_queries and performance_by_date. It does not explicitly name how it differs from query_search_analytics, which also returns ranked results, but the 'landing pages' phrasing is a meaningful disambiguator.

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 alternatives (top_queries, query_all_rows), and no stated prerequisites such as needing a valid site_url or an accessible property. The agent must infer all of this from the name and 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 behavioral burden, and it only discloses the click-based ordering. It says nothing about authentication requirements, rate limits, pagination, or whether results are truncated at row_limit, all of which matter for an analytics retrieval 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?

The single sentence is front-loaded and free of filler, but it is arguably under-sized rather than concise for a six-parameter analytics tool. Nothing is wasted, yet too little is said.

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 schema thoroughly documents parameters. However, with zero annotations and no usage or behavioral context, the definition leaves an agent without enough to confidently choose this tool over its many 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 100%, so every parameter including the filters object and the default 28-day date window is already documented in the schema. The description adds no parameter-level meaning beyond the click-ordering hint, making 3 the correct 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 names a specific resource (search queries) and a ranking metric (by clicks) scoped to a property, which is enough to distinguish it from siblings like top_pages or performance_by_date. It stops short of explicitly naming those alternatives, so it doesn't reach the top tier.

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 query_search_analytics, query_all_rows, or top_pages, and no mention of prerequisites. The agent must infer usage purely from the name and resource.

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