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

Annotations indicate readOnly=false, destructive=false, idempotent=true. The description adds crucial context: adding without verification results in siteUnverifiedUser and 403 errors on data calls, making the side effects and limitations clear.

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 resource, then immediately noting the caveat and alternative. No wasted words, all sentences serve a purpose.

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?

Explains the consequence of using this tool (unverified property) and provides the full alternative path via setup_site. Complete guidance for an agent deciding between add_site and setup_site, with output schema present but not needing explanation.

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 covers the single parameter site_url with a description including format examples. The tool description does not add extra parameter semantics beyond the schema, so baseline score of 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?

Clearly states the action 'Adds a property to Search Console' with a specific resource. Distinguishes from sibling setup_site by explicitly noting it does NOT verify ownership, so the agent understands the difference.

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

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

Explicitly says when to use this tool (to add a property) and when to use setup_site instead. Provides a sequence of operations (get_verification_token → verify_site → this) to achieve a working property.

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?

The description explicitly states the destructive action (removes a property) and the confirmation-token mechanism, which safely discloses the multi-step removal process. The annotations already indicate destructive and idempotent, and the description adds useful procedural detail without contradiction.

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 two clear sentences with no unnecessary details. It efficiently conveys the core purpose and the two-step process, making it easy for the agent to understand the tool's behavior.

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

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

The description is sufficient for an agent to invoke the tool correctly: it states that the first call returns a token and the second performs the removal. It does not cover edge cases like non-existent properties, but the output schema is available and the annotations cover safety aspects, so overall context is adequate.

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

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

The schema descriptions for both parameters are complete and already explain the confirmation-token flow. The tool description echoes this but does not add significant additional meaning beyond what the schema provides, so it meets the baseline for 100% 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 tool name, title, and description all clearly state that this tool removes a property from Search Console. The distinction from sibling tools like unverify_site and add_site is implicit, and the two-step nature is described.

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

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

The description explains the two-step workflow (first call returns a token, second call performs the removal), which is a key usage guideline. However, it does not explicitly compare with sibling tools or mention prerequites like ownership verification, so some context is missing.

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?

Beyond the annotations (destructiveHint), the description discloses important behavioral details: the confirmation token mechanism, the need to call without the token first, and that the token cannot be guessed or reused. This is significant behavioral information not captured in the annotations.

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

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

The description is concise, with two sentences that front-load the primary action and then explain the flow. No unnecessary words or 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 explains the two-step token flow, which is critical for correct usage. It does not mention error cases or permissions, but the output schema exists and annotations cover destructive behavior. The essential context for an agent to use the tool is present.

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 input schema descriptions fully cover all three parameters (feedpath, site_url, confirm_token) with clear meanings. The description adds no extra parameter-level detail beyond what is already in the schema, so a baseline score of 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 clearly states the tool's action: 'Removes a sitemap from the property.' It uses a specific verb ('Removes') and resource ('sitemap'), and distinguishes it from sibling tools that delete sites or manage verifications. The two-step nature is also mentioned, adding clarity.

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

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

The description provides explicit guidance on the two-step process: first call returns a confirmation token, second performs the removal. This is a practical usage instruction. However, it does not explicitly compare to alternatives (e.g., when to use delete_sitemap vs delete_site), but the purpose is clear enough.

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

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

Annotations already indicate read-only/idempotent/non-destructive. The description adds the 403 failure mode and ownership requirement, but does not mention pagination or output format; still strong given 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?

Three concise sentences, each carrying distinct useful information: what it returns, what it does not return, and the access requirement. No wasted words.

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

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

Given only one parameter and a clear read-only purpose, the description is nearly complete. Missing output schema details or example response, but not essential for selection or invocation.

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

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

The schema covers the url parameter with its maxLength, and the description implies it is the URL whose notification history is queried. No extra detail like URL format or examples, but adequate.

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

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

The description clearly states the tool returns notification history timestamps and types for a URL via the Indexing API, and distinguishes it from inspect_url by explicitly saying it does not report indexing status.

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

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

It explicitly contrasts with inspect_url and notes the credential requirement (verified owner vs Search Console user), giving clear guidance on when to use this tool and what prerequisite is needed.

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?

The description aligns with the readOnly, idempotent annotations and adds the behavior of returning the credential's permission level, which is not stated in annotations but is consistent and useful.

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

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

The description is exceptionally concise—two sentences—yet conveys the purpose, use case, and key distinction without fluff.

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

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

Given the presence of an output schema and a single parameter, the description fully covers what the tool does and why it exists; no additional context is needed.

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 only parameter site_url is fully described with examples and a note about required trailing slash, matching the schema description exactly and leaving no ambiguity.

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

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

The description clearly states the tool returns one property and its permission level, and distinguishes between domain and URL-prefix properties, which is precise and sets it apart from list_sites and get_verified_site.

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

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

It explicitly mentions a practical use case—settling which spelling of a property exists—and implies when to use this tool over listing or verification-specific tools, providing clear 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?

The description is read-only and idempotent-consistent with the annotations, and it adds useful detail about the returned error information. It does not mention rate limits or authorization, but the annotations already cover the main safety aspects.

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 concise sentences with no redundant wording. The key information is front-loaded and the added contrast with submit_sitemap is valuable.

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 complete for a simple read operation: it names the parameters, the returned record contents, and the primary use case. No additional context is needed to invoke 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?

The schema provides strong descriptions for both parameters, including examples and required trailing-slash behavior for site_url. The description itself adds little beyond the schema, but the schema coverage is complete.

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

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

Clearly states it returns the full record for a single submitted sitemap, and distinguishes this from submit_sitemap by noting that errors appear here rather than in the submit response. This makes the tool's purpose unmistakable.

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 tells when to use this tool: to check whether a sitemap submission actually worked. It also contrasts with submit_sitemap, helping an agent choose between related sibling 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?

Annotations already mark readOnly/idempotent, and the description adds explicit side-effect clarity: 'Nothing is created and nothing is claimed by this call.' It also explains the safe no-op behavior for unowned domains and that token placement is a human step, going beyond the annotations.

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

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

The description is slightly verbose, with three paragraphs and some repeated emphasis on non-creation and ownership proof, but each sentence does carry useful operational detail. It could be tightened without losing information, but it remains focused.

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

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

Given the tool has only two parameters, an output schema, and detailed property/method semantics, the description covers all necessary invocation context. It explains the relationship to verify_site, the human placement step, and the property-kind-specific behavior, making the tool self-contained for an agent.

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

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

The schema already defines both parameters with descriptions, and the tool description adds valuable defaults and constraints: method defaults to the sensible option per property kind, and site_url includes exact format examples with required trailing slash for URL-prefix. This fully compensates for any schema ambiguity.

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 the specific function: 'Returns the token that proves ownership of a site, and says exactly where to put it.' It clearly differentiates from sibling verification tools by noting it creates no state and that verify_site is the next step after token placement.

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

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

It gives concrete when-to-use and when-not-to-use guidance: DNS/META vs FILE selection, and explicitly says ANALYTICS and TAG_MANAGER have no token to fetch and should go directly to verify_site. It also warns that running against an unowned domain 'just achieves nothing,' helping agents avoid pointless calls.

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?

The description adds meaningful behavior beyond annotations by specifying the return includes owner emails and the id type. It aligns with readOnly/idempotent hints and doesn't mention side effects.

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

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

The one-sentence description is succinct, direct, and free of extraneous information.

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

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

While the description covers the basic purpose and output relevance, it doesn't address error cases or explicitly distinguish from get_site in usage. It's adequate but not comprehensive.

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 input schema already fully describes the 'id' parameter, including its format and source. The tool description adds no additional parameter-specific meaning.

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

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

The description clearly states the tool returns a single verified site and its owners' emails. It differentiates itself from get_site by specifying 'verified' and including owner emails, though it doesn't explicitly contrast with sibling tools.

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

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

The description provides no guidance on when to use this tool versus alternatives like list_verified_sites or get_site. It lacks explicit conditions or context.

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

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

Beyond the readOnlyHint and idempotentHint annotations, the description adds meaningful behavioral details: results reflect Google's last known state, not a live fetch, and quota consumption can block further inspections for the rest of the day. This gives the agent a clearer picture of side effects and limitations.

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 moderately detailed but every sentence carries useful information—scope, data source, and quota behavior. It is somewhat longer than strictly necessary but remains focused and well-structured.

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

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

The description is complete for practical use: it explains what the tool does, the staleness caveat, and the quota limits. Since an output schema exists, omitting response details is acceptable, and the provided context covers the key operational aspects.

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 input schema already provides complete descriptions for all three parameters, including format examples for site_url and the language_code default. The description does not add further parameter-level detail, so it stays at the baseline for schema-covered parameters.

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

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

The description states a specific action—asking Google about one URL—and enumerates the exact information returned (indexing, crawl date, sitemaps, canonical, robots.txt, mobile-usability, rich results). It clearly identifies the tool's scope as a single-URL inspection, which distinguishes it from broader analytics or site-level tools.

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

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

The description provides important usage caveats, such as the fact that it reports the last indexed state rather than a live fetch, and explains the daily quota behavior. However, it does not explicitly contrast this tool with the sibling 'inspect_urls' tool or state when to prefer one over the other, leaving some usage guidance implicit.

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?

The annotations already establish read-only, idempotent, and non-destructive behavior. The description goes beyond this by disclosing that one failing URL does not stop the rest, that results are condensed, and that exceeding the daily budget blocks further inspection for the day. These are meaningful behavioral details not present in the annotations.

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

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

The description is tight and information-dense, with no redundant filler. It front-loads the core purpose and then adds the most relevant usage and operational caveats in a compact second paragraph. Every sentence contributes useful information.

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

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

Given that an output schema is provided and the key behavioral caveats are covered, the description is complete for practical use. It tells the agent what the tool does, how it differs from inspect_url, what to expect in terms of failure behavior, and the relevant quota/rate constraints, so no critical context 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?

The input schema already describes all three parameters in detail, including site_url format, language_code BCP-47, and inspection_urls constraints. The description adds little to parameter semantics beyond reinforcing the 'up to 20' and 'same property' ideas already present in the schema. With full schema coverage, a baseline score of 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 clearly states that the tool inspects up to 20 URLs in a single logical call and reports a per-URL verdict. It also distinguishes itself from the sibling inspect_url tool by noting it is the batch/condensed variant, so the purpose 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?

The description explicitly advises using inspect_url when a full report is needed, notes that the API has no native batch method, and explains the round-trip savings. It also gives concrete operational guidance about the 2,000-call daily budget and 600-per-minute rate limit, making when and how to use the tool clear.

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

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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds meaningful behavioral details such as the lack of an update endpoint, idempotent re-submission, and the removal of the ping endpoint, which goes beyond the annotations without contradicting them.

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

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

The description is concise and front-loaded with the core purpose, followed by useful behavioral and parameter notes. Every sentence adds information without redundancy or fluff.

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

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

The description provides enough context for correct usage: what is returned, how the optional parameter changes results, how to refresh, and what cannot be done (forced re-crawl, ping endpoint). Given the annotations and output schema presence, nothing essential 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?

Both parameters have thorough schema descriptions, and the description further clarifies the effect of sitemap_index and the default filtering behavior. This fully covers the parameter semantics.

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

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

The description clearly states the tool lists sitemaps submitted for a property and details the returned information (last download, URL counts, warnings/errors). It distinguishes this listing operation from other sitemap actions like submission or deletion.

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

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

It explicitly explains the behavior of the optional sitemap_index parameter, notes that only directly submitted sitemaps are returned by default, and clarifies that refreshing is done by re-submitting the same URL rather than a separate update call. This gives clear practical 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?

The annotations already convey read-only, idempotent, non-destructive behavior, and the description adds meaningful context beyond them: permissionLevel meanings, the unverified-property state, and that data calls for unverified properties return 403. This helps the agent understand real-world behavior without contradicting annotations.

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

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

Every sentence earns its place: the first sets scope and output, the second gives a diagnostic trigger, and the third defines permission levels. The most important usage guidance is front-loaded, and there is no filler or repetition of schema details.

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 parameters, no required input, and an output schema already present, the description fully covers what an agent needs to call this tool correctly. It explains the output semantics, edge cases, and the recommended diagnostic workflow, leaving no obvious 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?

The tool has zero parameters, so the baseline for this dimension is 4. The description cannot add parameter-level semantics, but it enriches the meaning of the permissionLevel values that appear in the output, which is useful context.

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: lists every Search Console property the credential can see, with the permission level on each. It clearly differentiates from siblings like list_verified_sites by explicitly including unverified properties and by focusing on what the credential can access.

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 a strong, concrete trigger: the first call to make when anything returns 403. It also tells the agent how to interpret an empty list for fresh service accounts, but it does not explicitly name sibling alternatives or state when not to use this tool.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: the list is scoped to verified ownership, includes the full owner list per site, and is semantically distinct from property membership. No contradictions with annotations.

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

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

Three sentences, all substantive: the first states the core function, the second resolves the most likely confusion with list_sites, and the third adds useful cross-tool context. No filler or 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?

With zero parameters and an output schema present, the description fully covers what an agent needs to decide when to call this tool: the exact list scope, the owner list detail, and the distinction from list_sites. The setup_site reference further completes the contextual picture.

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 input schema has zero parameters, so there is no parameter ambiguity. Baseline for zero-parameter tools is 4; the description correctly focuses on what the tool returns rather than inventing parameters to explain.

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

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

The description uses a specific verb ('Lists') and clearly identifies the resource: every site this credential has verified ownership of. It explicitly distinguishes itself from list_sites, so an agent can tell them apart without inspecting 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?

The description explicitly contrasts list_verified_sites with list_sites: list_sites returns Search Console properties, while this returns proven ownership, and a site may be in either list independently. It also notes that setup_site compares the two, giving the agent concrete routing context.

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

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds important behavioral context: data is 2–3 days behind, only 16 months retained, rows may not sum due to anonymization, and hourly data needs special settings. This extra context is valuable and does not contradict annotations.

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

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

The description is tightly organized into three short paragraphs, each covering a distinct concern: result contents, date/data freshness, and pagination/anonymization. Every sentence contributes precise, non-redundant information, making it highly efficient and easy to parse.

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

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

Given the tool's complexity (12 parameters, 5 enums, 1 required) and full schema coverage, the description rounds out the picture with high-level intent, limitations, and operational caveats. It also benefits from an output schema being present, so the lack of return-format detail is acceptable. No gaps remain for effective usage.

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 schema already covers 100% of parameters, setting a baseline of 3. The description adds meaningful semantic nuance, such as the mutual exclusivity of period vs. start_date/end_date, the practical advice on row_limit vs. start_row for paging, and the specific field format expectations. This goes beyond restating 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 clearly states that the tool returns clicks, impressions, CTR, and average position from Google Search, and explicitly identifies it as the Performance report exposed as an API. This is a specific verb-resource-purpose combination that distinguishes it from sibling tools.

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 explicit guidance on date range selection (period vs. start_date/end_date), notes data finalization delays and retention limits, and explains row_limit paging and the anonymization caveat with query dimension. It also advises when to omit query for true totals, providing actionable usage direction.

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?

Beyond the annotations (idempotentHint=true, destructiveHint=false), the description explains actual behavior: the call succeeds but changes nothing for non-qualifying pages, returns a timestamp, triggers a 403 without specifying the cause for insufficient credentials, and enforces a 200 URL/day quota. It also notes that URL_DELETED requires the page to return 404 or 410.

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 well-organized and concise. Every sentence adds value: purpose, limitations, credential requirements, and quota. No redundant or vague phrasing. The structure flows logically from action to constraints to usage notes.

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 nuanced behavior, the description covers all essential context: when it works (structured data types), when it doesn't (normal pages), error conditions (403), and operational limits (quota). It also clarifies the distinction from sitemap submission. The presence of an output schema is sufficient; the description does not need to explain return values.

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 schema description coverage is 100%, with both parameters fully described. The description text does not add extra meaning beyond the schema, but the schema itself already provides sufficient semantic detail (e.g., type enum with default and URL_DELETED requirement). Baseline for high coverage 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 clearly states the tool's purpose: to notify Google of URL updates or removals via the Indexing API. It specifies the exact action ('Tells Google... that a URL was updated or removed') and distinguishes it from related tools like submit_sitemap by explicitly noting it is not for normal page crawling.

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

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

The description provides explicit usage guidance: it only works for pages with JobPosting or BroadcastEvent structured data, and for other pages users should submit a sitemap. It also mentions credential requirements (verified owner) and quota limits, giving the agent clear conditions for when to use this tool versus alternatives.

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

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

The description explicitly states the tool reads current state, reports the next step, and changes nothing. This aligns with the annotations readOnlyHint=true, idempotentHint=true, and destructiveHint=false. It reinforces the annotations without contradicting them, and adds useful context about what kind of output to expect.

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 somewhat repetitive—the first and third paragraphs both say the tool reports the next step—but each paragraph carries useful information about the setup process, the 403 pitfall, and the tool's non-mutating nature. It is slightly longer than necessary but remains focused and readable.

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 provides enough context for an agent to understand when and why to invoke this tool, especially given the sibling tools and the warning about add_site. An output schema is present, so return-value details do not need to be spelled out. The tool's role within the verification workflow is well explained.

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

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

The single parameter site_url is fully documented in the schema, including the distinction between sc-domain and URL-prefix formats and the trailing-slash requirement. The description does not add additional parameter meaning beyond the schema, so a baseline score of 3 is appropriate given 100% 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 clearly states the tool's diagnostic role: it works out where a property stands and reports the next step in the verification/setup process. It distinguishes itself from action-oriented sibling tools like add_site or verify_site by emphasizing it reads state and gives guidance rather than performing setup.

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 practical usage context by explaining the four-step verification order and warning that calling add_site prematurely succeeds but leaves the property returning 403. This effectively tells an agent when to use this tool: to determine the correct next step before taking action. It does not explicitly name alternatives, but the guidance is strong.

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?

The description transparently explains that a successful call only means the address was accepted, not that the sitemap is valid, and that parse errors will appear later in get_sitemap. This sets accurate expectations about the tool's behavior and its effects, complementing the idempotentHint annotation.

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

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

The description is concise yet comprehensive, covering purpose, idempotency, expectations, and error handling in a well-structured manner. Every sentence adds value without unnecessary verbosity.

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 submission tool, the description provides complete context: what it does, how to refresh, what success means, and how to check for errors later. It also includes relevant historical context about the ping endpoint, making it self-sufficient for an agent.

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

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

The input schema already provides thorough descriptions for both site_url and feedpath, covering 100% of the parameters. The tool description does not add additional parameter-specific details beyond what the schema already states, so the baseline score 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 clearly states the tool's purpose: submitting a sitemap URL or resubmitting an existing one. It distinguishes the action and provides context about idempotency, leaving no ambiguity about what the tool does.

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

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

Explicit guidance is given: resubmit the same URL to refresh, no separate update call exists, and the action is idempotent. It also sets expectations about Google's crawling schedule and the removal of the ping endpoint, which is valuable for correct usage.

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?

Beyond the annotations (idempotent, non-destructive), the description adds useful behavioral details: per-entry success/failure reporting and partial failure isolation. This helps the agent understand what to expect in mixed-result scenarios.

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

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

The description is concise and well-structured, conveying all essential information without unnecessary padding. It efficiently covers purpose, batch behavior, and failure handling in a few sentences.

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 that an output schema is present, the description need not detail return values. It adequately covers the core operation, including limits and partial failure, making it self-contained for the agent.

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

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

Schema description coverage is 100% for both parameters, providing clear meaning. The tool description itself does not add further parameter-specific clarification, so a baseline of 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 clearly states the action (submit sitemaps), the resource (sitemaps), the scope (up to 50 for one property), and the batch nature. It distinguishes itself from the sibling submit_sitemap by emphasizing 'single call' and per-entry reporting.

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

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

It explains the trade-off between this batch tool and making individual calls, noting that it saves round trips while not being a true server-side batch. This gives context for when to use it, though it doesn't explicitly say 'use this when you have multiple 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?

Goes well beyond the annotations by disclosing the confirmation-token flow, the need to call without the token first, and that the token cannot be guessed or reused. This directly prepares the agent for the tool's unusual interactive behavior.

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

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

The description is concise and front-loaded with the core purpose, followed by the essential two-step usage detail. Parameter descriptions are thorough without being overly 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?

The description provides enough context for an agent to know when to use the tool and how to sequence the calls. With an output schema present and clear parameter descriptions, no critical information appears 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?

Both parameters are fully described with valuable context. The id description clearly distinguishes the verification resource id from a property URL, and confirm_token explains its source and lifecycle.

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

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

Clearly states a specific action: removes a credential/ownership from a site. The title 'Remove ownership' reinforces the purpose and distinguishes it from other site/sitemap tools.

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

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

Explains the two-step invocation pattern: first call without confirm_token returns a token, second call performs the removal. However, it does not explicitly contrast this with related tools like delete_site or update_site_owners.

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?

Beyond the annotations (destructiveHint=true), the description discloses the replacement semantics, the accidental-wipe guard that refuses empty lists, and the two-step confirmation-token behavior. This gives the agent actionable knowledge it would not get from annotations or schema alone.

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

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

The description is front-loaded with the core behavior and then layers warning and workflow details in a clear order. It is longer than strictly necessary, but each section serves a purpose: replacement semantics, safe-list construction, and two-step flow.

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 a rich output schema and annotations present, the description covers the remaining operational gaps: preconditions, destructive behavior, and confirmation flow. No important calling detail appears missing for this 4-parameter mutation tool.

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

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

Schema coverage is 100%, so the schema already documents each parameter. The description adds useful operational context: 'Call get_verified_site first and send back the existing addresses plus the new one' clarifies how to construct owners, and 'the first call returns a confirmation token' clarifies confirm_token. It earns above the baseline 3 without replacing 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 opens with a specific verb and resource: 'Replaces the list of verified owners of a site.' It immediately distinguishes itself from add-style operations by stating 'It REPLACES rather than adds', and the title 'Change the owner list' is clarified by the first line. An agent can tell this from sibling tools like get_verified_site or unverify_site.

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

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

It gives explicit when-to-use context: it is how a second person or service account is granted ownership without their own token. It also provides a required precondition and workflow: call get_verified_site first, send back existing addresses plus the new one, and understand the two-step token process.

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

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

Annotations already provide idempotentHint=true and destructiveHint=false, and the description adds meaningful context beyond them: the tool only checks and places nothing, and failures are usually transient propagation delays rather than invalid input. The DNS/CDN propagation explanation gives an agent a concrete retry model that annotations alone cannot convey. No contradiction with annotations.

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

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

Two tight paragraphs: the first states the action and the prerequisite, the second explains failure semantics and the expected retry response. Every sentence earns its place — no filler or repetition of schema content. The most decision-relevant fact (this call only checks) 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?

For a 2-parameter tool with annotations covering idempotency and destructiveness, plus an output schema, the description is nearly complete. It covers the prerequisite workflow, the failure mode, and the retry guidance an agent needs to act correctly. The only minor omission is explicit guidance on what distinguishes verification from unverification or site setup, though the core call path is fully specified.

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

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

Schema description coverage is 100%, with both method and site_url already documented including defaults, examples, and the trailing-slash requirement. The description references the token placement workflow that contextualizes the method parameter but adds no parameter-level detail beyond the schema. Baseline 3 is appropriate since the schema carries the parameter documentation burden.

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 result: "Tells Google to check for the verification token and, if it finds it, records this credential as an owner." This clearly distinguishes verify_site from sibling get_verification_token by explicitly noting "this call only checks, it does not place anything." The scope (verification versus token retrieval, site addition, or unverification) 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?

The description gives explicit workflow guidance: "Run get_verification_token first and place the token" — establishing the prerequisite and ordering relative to a specific sibling. It also tells the agent how to interpret failures and that retrying is the normal response. It does not explicitly state when NOT to use this tool vs alternatives like add_site or unverify_site, but the usage context is well-defined.

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