SEO GSC Wizard MCP

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

Discloses a non-obvious behavioral trait beyond the annotations: rows are APPENDED, never deduplicated, so re-sending the same list stores it twice, with the remedy (delete first). Annotations only cover the safety profile (readOnly/destructive/openWorld), so this append semantics detail is genuinely additive.

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

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

Front-loaded with the core action, then routing and the append caveat. Four sentences that mostly earn their place, though the compare_migration reference is slightly more verbose than needed.

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?

Complete for this tool: output schema exists so return values needn't be described, annotations cover the safety profile, and the description supplies the append/dedup caveat, sibling routing, and label grouping semantics.

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

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

Schema description coverage is 75%, so the schema already documents siteUrlA/B, redirects, and label. The description reinforces A/B as source/target and explains label as the mechanism to keep migrations apart on one account, but adds no syntax or format detail beyond the schema.

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

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

States a specific verb and resource ('Saves redirect mappings (old URL -> new URL) for a site migration') and ties it to the source/target properties. It clearly distinguishes itself from siblings compare_migration (read) and delete_migration_redirects (clear).

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

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

Explicitly routes the agent: use compare_migration for the before/after read, use these mappings to record old->new, and clear a set first with delete_migration_redirects when re-uploading. Both the when-to-use and the alternative 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?

Annotations only flag readOnly=false, destructive=false, openWorld=true; the description adds substantial non-obvious behavior: tracker is created if absent, domain membership is enforced, the 1,800-URL cap silently skips and reports overflow, and new entries land in a 'pending' state. This is exactly the kind of side-effect and state-transition detail annotations cannot express.

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, front-loaded with the core action, then constraints, then next-step guidance. Every sentence carries distinct, load-bearing information 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?

An output schema exists so return-value explanation is unnecessary, and the description still covers creation behavior, the domain constraint, the cap edge case, and the resulting URL state. An agent has everything needed to call it correctly and interpret the outcome.

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

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

Schema coverage is 0%, so the schema alone leaves the two parameters under-explained. The description compensates by clarifying that each URL must belong to the property's domain and that the 1800 limit is enforced with skip-and-report semantics rather than schema-level rejection, though it does not say what siteUrl format (property vs. full URL) is expected.

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 ('Adds URLs to the GSC Wizard Indexing Tracker for a property') and includes the auto-creation scope detail. It also names the follow-up sibling check_tracked_url_now, letting an agent distinguish this ingest tool from the inspection 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?

Provides clear operational context: URLs must belong to the property's domain, the 1,800 cap causes skips that are reported, and newly added URLs can be inspected via check_tracked_url_now rather than waiting for the hourly cron. It stops short of an explicit when-not-to-use statement (e.g., versus submit_indexnow_urls), so it falls just short of 5.

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

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

Annotations cover only safety (readOnly/openWorld), and the description adds real behavioral depth beyond them: the data-source fallback (ClickHouse warehouse else live Search Console API), the heuristic limitation ('judges how a query LOOKS, not what the searcher meant'), the single-row caveat, and the ~2-3 day settling lag.

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 purpose is front-loaded in the first clause, followed by the taxonomy, then returns, then caveats and defaults. It is long, but every sentence carries information; the bucket parenthetical examples slightly pad the length.

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 6-parameter analytical tool with an output schema, an agent has everything needed: what it computes, the allowed buckets, the date defaults and lag, the data-source fallback, and the interpretation caveat. Return values are covered by the output schema and additionally summarized.

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

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

Schema coverage is 67% and the description compensates: it enumerates the conceptual bucket groups with example queries, restates the optional date-range default behavior, and explains the aiShaped roll-up. It does not describe siteUrl or searchType, but the remaining schema descriptions are 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?

States a specific verb (classifies by SHAPE) and resource (a property's queries) with a clearly named goal (surfacing AI Overviews / AI Mode fan-out fingerprints). The bucket taxonomy and the aiShaped roll-up make it unmistakably distinct from siblings like get_query_shape_trend or query_top_queries.

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

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

Explains the context of use (the app's Query Analysis report) and gives concrete operating instructions — omit dates for last 28 settled days, data lags 2-3 days. It does not explicitly name a sibling alternative or state when NOT to use it, so it falls short of a 5.

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

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description's job is lighter. It adds real value by disclosing the default account-level visibility, the siteUrl scoping behavior, and the reserved platform-wide scope — none of which the annotations convey.

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

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

Three short sentences, front-loaded with the core action, then scope semantics, then the exclusion. Every sentence carries information and none is redundant.

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, and the safety profile is covered by annotations. The description is complete enough for an agent to call the tool correctly, with the main residual gap being its silence on the non-required fields.

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

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

Schema coverage is only 43% across 7 parameters, so the description is expected to compensate, but it only touches siteUrl — and largely repeats that parameter's own schema description. Terms like label, color, category, and description receive no clarification the schema doesn't already imply, leaving the low-coverage params underspecified.

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 ('Adds a chart annotation'), which is unambiguous against siblings like list_annotations, update_annotation, and delete_annotation. It does not, however, explicitly name a sibling or contrast with one, so it stops short of a 5.

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

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

Gives clear context: account scope is the default, pass siteUrl to narrow to a property, and platform-wide annotations are not creatable here. That last clause is a genuine when-not condition. It stops short of a 5 because it never names an alternative tool or workflow.

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

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

Annotations already establish readOnlyHint=false (a write) and destructiveHint=false, so the safety profile is covered. The description adds real behavioral value beyond that: a newly saved preset is inert until picked, and it surfaces in the property's presets. It does not mention error modes or duplicate-name handling, keeping 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?

Three sentences, front-loaded with the core action, then parameter semantics, then the key side-effect caveat. No filler and nothing repeated from the schema verbatim.

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, and the description supplies the essential side-effect behavior plus the shape reference for `filters`. It omits any auth/permission context and does not mention the idempotency behavior, which the schema covers for clientRequestId.

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

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

Schema description coverage is 60%, so the schema documents enum values and the filterLogic toggle reasonably well. The description adds a meaningful cross-reference by stating `filters` matches the shape that list_saved_filters returns, which helps an agent build the array. It does not cover the undocumented name/siteUrl parameters, so it falls short of full compensation.

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: 'Stores a filter preset against a property.' It also clarifies the intended analogue ('as the dashboard's filter panel would'), which removes ambiguity about what a preset is. It stops short of explicitly contrasting with update_saved_filter or delete_saved_filter, so sibling differentiation is only implicit via the referencing of list_saved_filters.

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 (create a new preset that appears in the property's filter presets) but there is no explicit when-to-use versus update_saved_filter, nor prerequisites such as required scopes or property setup. The caveat that saving 'does not apply it to anything on its own' is genuinely useful context, though it describes effect rather than selecting between tools.

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

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

Annotations only declare readOnlyHint=false and destructiveHint=false. The description adds genuinely non-obvious behavior: idempotency with alreadyExisted: true returned instead of an error, name uniqueness per property, and that keywords are stored as text and matched against GSC queries. This exceeds what structured fields disclose.

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

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

Front-loaded with the core action and effect, then the idempotency rule and sibling routing. Every clause 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 format need not be spelled out, and the description still highlights the alreadyExisted flag. It omits permission/scope requirements and behavior on invalid input (e.g., empty or oversized keyword lists), leaving minor gaps for a write tool.

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

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

Schema coverage is 0%, so the description must carry parameter meaning. It explains name (unique per property, with the already-exists consequence) and keywords (stored as text, matched against GSC queries); siteUrl's role is only implied by "on a property" and the 1000-keyword ceiling is left to 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+resource+effect: "Creates a topic cluster on a property by grouping keywords under a name." It distinguishes itself from update_topic_cluster and list_topic_clusters by scoping to creation/grouping, so an agent can route 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?

Explicitly names the alternative ("Use update_topic_cluster to change an existing cluster's keywords") and states the condition that selects it, plus the idempotent already-exists case so the agent knows a duplicate call needs no retry.

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 destructiveHint=true, so the destructive nature is covered. The description adds real value beyond the annotations by disclosing an authorization/ownership constraint on which annotations are eligible for deletion.

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

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

Two tight sentences with the core action front-loaded and the constraint following immediately. 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 needn't be explained, and the destructive annotation covers the safety profile. The ownership constraint completes the practical picture; only edge cases like deleting a non-existent id are left unaddressed.

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

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

Schema coverage is 0%, so the schema documents nothing about the single annotationId parameter. The description adds only 'by id', confirming the param's role but giving no format or sourcing guidance beyond the uuid type already in 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 ('Deletes') and resource ('chart annotation') scoped by id. The purpose is unmistakable, though it does not explicitly name or contrast with siblings like create_annotation, update_annotation, or list_annotations.

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 clear exclusion: only user-owned annotations can be removed, while platform-scoped annotations cannot be deleted via this tool. This tells the agent when NOT to use it, though it doesn't route to alternatives (e.g., list_annotations to discover ids).

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 flag destructiveHint=true, but the description adds the critical guard behavior: unnarrowed deletes are blocked unless confirmDeleteAll is passed, and deletions are permanent. This is genuine behavioral context beyond the 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?

Three sentences, all load-bearing: purpose, narrowing + guard, and the preview recommendation. The destructive scope 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?

An output schema exists, so return values need not be explained. For a destructive, no-required-param tool, the description covers everything an agent needs to call it safely.

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 baseline is 3, but the description adds the interplay between filters and confirmDeleteAll (that the flag is required precisely when no filter is supplied) and explains the A/B pair as source/target property narrowing.

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+resource ("Permanently deletes saved redirect mappings") and its scope is unmistakable. It is clearly distinguishable from the sibling add_migration_redirects and from the read-only list_migration_redirects.

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 states exactly when to narrow (label and/or A/B property pair), when confirmDeleteAll: true is mandatory, and why (an unnarrowed delete would also wipe unrelated migrations). It also routes the agent to list_migration_redirects with the same filters as a preview step.

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 destructiveHint=true annotation by naming the cascade (all client grants destroyed), the external impact (existing shared links break for holders), the permanence of deletion, and the ownership authorization requirement. This is exactly the extra context a mutation tool needs.

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 tight sentences with the destructive effect front-loaded, followed by the authorization constraint and the id-lookup hint. No filler and no repetition 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?

With an output schema present, return values need no explanation, and the annotations already cover the safety profile. The description supplies the remaining essentials: cascade scope, irreversibility, ownership gate, and id provenance.

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

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

Schema coverage is 0%, so the description must carry the load. It tells the agent where the reportId comes from (list_shared_reports) without restating the raw name, but does not describe the expected format or what happens on a malformed/unknown id.

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 (permanently deletes) and resource (a saved shareable report) and quantifies the effect: every client grant is removed and the shared link breaks. This clearly separates it from siblings like delete_saved_filter, delete_content_group, and delete_annotation.

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

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

Gives an explicit precondition (only reports owned by the authenticated user) and routes the agent to list_shared_reports for obtaining the id. It lacks an explicit when-not-to-use case (e.g., revoking access for one client via manage_report_access), but the context is otherwise unambiguous.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds genuine behavioral context beyond them: single round trip, shared auth + property resolution, server-side parallel reads, and ClickHouse warehouse sourcing when available. It does not discuss cost/rate limits of the heavy aggregate call.

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

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

Front-loads the core action in the first clause before the long section list, then closes with the performance rationale and format guidance. Every sentence carries information, though the parenthetical section catalog is dense.

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

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

Output schema exists so return values need not be described, annotations cover the safety profile, and the description still supplies the aggregate-vs-single-tool framing and format semantics. Nothing an agent needs to select or invoke this correctly is missing.

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

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

With 75% schema coverage, the schema already documents days, siteUrl and includeSitemap. The description adds meaning to the format enum by explaining html = ready-to-open report versus json = underlying data bundle, which the bare enum does not convey.

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 ('Runs the full analysis suite for one property in a single call') and enumerates the sections produced (overview, top queries/pages, CTR curve, cannibalization, etc.). It is clearly distinguishable from the individual analyze_* / get_* siblings by explicitly framing itself as the one-call aggregate.

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 contrasts with the alternative workflow ('far faster than calling each analysis tool separately') and gives format selection guidance (html default vs json for the data bundle). It lacks an explicit when-not-to-use statement (e.g. when you only need one section), so it falls short of the top mark.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds useful context beyond that by disclosing the payload contents (email, scopes, subscription) and the intended diagnostic role, though it says nothing about auth requirements or behavior when accounts are missing.

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, both earning their place: the first enumerates the return payload, the second routes the agent to the right moment to call it. Front-loaded with the substantive content and free of 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?

With an output schema present, the description is not obliged to detail return structure, yet it still summarizes the payload and gives the agent a clear reason to invoke the tool. For a zero-parameter read operation this is 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?

Zero parameters, so per the rubric the baseline is 4. There is no parameter surface for the description to illuminate, and it does not need to compensate for any schema gaps.

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 (returns) and enumerates the exact resource set: authenticated user, connected Google accounts with email + scopes, and subscription status. No sibling tool surfaces account/auth state, so it is unmistakably distinct from the list_* and get_* analytics tools around it.

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 frames the use case as a diagnostic first call to verify the server is wired up and expected data sources are present. It does not need to name alternatives, since nothing else in the sibling set returns account context, but it stops short of stating any exclusions or failure conditions.

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/openWorldHint, so the safety profile is covered. The description adds genuinely extra behavior beyond the annotations: the per-row output shape (HTTP code, inbound-link count, decoded labels) and the notConfigured:true fallback when no Bing Webmaster API key exists — useful edge-case disclosure.

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

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

Two tight sentences, front-loaded with the core purpose and issue enumeration, then the fallback-state caveat. Every clause carries information; no padding.

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, return values needn't be restated. The description covers the resource, its issue taxonomy, and the missing-key edge case, so an agent has enough to call it correctly. The one omission is guidance on when to pick this over get_bing_crawl_stats.

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

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

Schema coverage is 50%: limit is well documented in the schema, but siteUrl has no description. The description adds only a loose hint ('for a property') that maps to siteUrl, and does nothing to clarify the limit semantics already in the schema. Adequate but with a clear gap it does not compensate for.

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

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

States a specific verb+resource ('URLs where Bing found crawl issues for a property') and enumerates the exact issue categories (4xx/5xx, redirects, robots.txt, DNS/timeout, malware) plus per-row fields. This detail naturally distinguishes it from the sibling get_bing_crawl_stats, which is aggregated counts rather than a per-URL list.

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, when-not, or alternative is named. Usage is only implied by the resource itself, and the sibling get_bing_crawl_stats (closest alternative) is never referenced. The stated notConfigured prerequisite is the only contextual 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?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavior: the default window is 'roughly the last 6 months' when dates are omitted, and the call degrades to notConfigured: true when no Bing Webmaster API key exists for the property — a failure mode annotations do not capture.

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

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

Front-loaded with the core purpose and scope, then a compact metric enumeration, then the notConfigured caveat. Two sentences, no filler. The metric list is long but each item is a distinct return dimension, so it earns its space.

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

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

Covers target, default window, returned metrics and the missing-API-key state for a read-only, single-required-param tool. Since an output schema exists, enumerating return fields in the description is optional rather than necessary, and pagination/cardinality behavior is unaddressed — minor gaps only.

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

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

Schema coverage is 67%: startDate and endDate are well documented in the schema (format, examples, 'never pass null'), while siteUrl has no description at all. The description partially compensates by calling the target a 'property', but it adds no date syntax, timezone, or window semantics beyond what the schema already states. 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 and resource (Bing daily crawl statistics for a property) and enumerates exactly which metrics come back: pages crawled, index size, inbound links, response-code breakdown, robots.txt blocks, crawl errors and malware flags. That level of specificity lets an agent separate it from neighbors like get_bing_page_stats, get_bing_link_counts and get_bing_crawl_issues.

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

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

Usage is only implied: an agent can infer this is the tool for crawl/indexing health of a Bing property, and the notConfigured note signals a prerequisite. But there is no explicit when-to-use statement, no exclusion, and no routing to alternatives such as get_bing_crawl_issues for issue detail or get_bing_page_stats for traffic.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavioral context beyond the annotations: the decoded status vocabulary and the special return 'notConfigured: true when no Bing Webmaster API key is set up', which lets the agent anticipate an auth-related edge case.

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?

Content is front-loaded and dense, with the field enumeration and the sibling comparison arriving early and no filler sentences. The two long sentences are somewhat packed, but every clause carries information (fields, statuses, counterpart, notConfigured 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?

With an output schema present, the description needn't detail return shapes, yet it still summarizes key fields and the notConfigured edge case, making the tool fully actionable. It is complete for a single-param read tool; only the siteUrl value expectation is left implicit.

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 one parameter (siteUrl) with 0% schema description coverage, so the description carries the burden but only implicitly references it via 'for a property'. The parameter is largely self-describing by name, so little is lost, but the description adds no format, URL-normalization, or example guidance that would compensate for the coverage gap.

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

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

States a specific verb+resource ('Sitemaps and feeds submitted to Bing Webmaster Tools for a property') and enumerates the returned fields so the agent knows exactly what data it gets. It explicitly distinguishes itself from the sibling list_sitemaps by calling itself 'the Bing counterpart', so an agent can route correctly without opening either schema.

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

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

The line 'The Bing counterpart to list_sitemaps' gives a clear context for when to reach for this tool over the general sitemap lister, which is strong routing guidance. However, it stops short of stating explicit when-not conditions or prerequisites (e.g., that a Bing property/API key must exist) beyond the notConfigured note.

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 and openWorldHint, so the safety profile is covered. The description adds genuinely useful context beyond that: it is not tied to any property (no siteUrl), and it returns notConfigured: true when no API key is configured, which surfaces an auth-state behavior an agent would otherwise miss.

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, front-loaded with the core purpose, then the property-independence, then the auth edge case. Efficient and no filler, though slightly dense.

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, return values need not be explained, and the description still covers the notable notConfigured case. Complete enough for a single-keyword read tool; a note on how it differs from sibling Bing query tools would close the remaining gap.

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

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

Schema description coverage is 100%, so country/language/keyword are already documented in the schema. The description adds only the negative detail that no siteUrl is needed, which is helpful but not parameter-level semantics beyond the schema 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?

States a specific verb+resource (historical impression volume for a single keyword) with scope qualifiers (weekly buckets, broad-match impressions) and explicitly anchors it to Bing Webmaster Tools marketplace data. Clear enough to distinguish from the sibling get_bing_query_stats/get_bing_query_page_stats calls.

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?

Says it is 'useful for gauging Bing search demand and seasonality,' which implies the use case, but never states when to prefer it over the many sibling Bing tools (e.g., get_bing_query_stats) or any exclusion conditions. Context is implied rather than spelled out.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is covered. The description adds genuinely useful non-annotation context: ~100 rows per page, the totalPages pagination signal, and the notConfigured: true behavior when no Bing API key exists for the property.

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

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

Three sentences, front-loaded with what the tool returns before covering pagination and the notConfigured edge case. Tight and free of repetition, though the parenthetical about ~100 rows is partly duplicated by the `limit` schema description.

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

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

An output schema exists, so return-value detail is not strictly required, yet the description still helpfully flags the totalPages and notConfigured fields. Combined with annotations covering safety, an agent has enough to call the tool correctly; the only gap is the undocumented siteUrl parameter.

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

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

Schema coverage is 67% and the schema already documents `page` and `limit` in detail with defaults and notes on large properties. The description reiterates the `page` semantics and adds totalPages, but does not compensate for the undocumented required `siteUrl` (only minLength: 1 in 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 and resource: inbound/backlink counts per URL recorded by Bing Webmaster Tools for a property. It is meaningfully distinct from siblings like get_bing_page_stats or get_bing_traffic_stats, though it does not explicitly name those siblings to sharpen the distinction.

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

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

Usage of the pagination parameter is explained (pass `page`, totalPages tells you how many pages exist), which implies the tool is a paginated listing. However, there is no guidance on when to choose this tool over the many other Bing/GSC data tools, and no exclusions or prerequisites beyond the notConfigured note.

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

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

Annotations already cover the safety profile (readOnlyHint, destructiveHint false, openWorldHint), so the bar is lower. The description adds real behavioral context beyond them: the exact-URL matching requirement and the notConfigured: true fallback when no Bing API key exists for the property. It does not discuss rate limits or quota consumption, which would have earned 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?

Four sentences, front-loaded with the tool's purpose, then the drill-down relationship, the URL pitfall, and the notConfigured edge case. Each sentence earns its place; the first is dense but not padded.

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, return-value documentation is not required, yet the description still clarifies that CTR is a 0-100 percentage and position is impression-weighted. It also covers the no-API-key edge case. Only a note on result volume/pagination beyond the schema's 'uncapped' limit 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 80%, so the schema already documents page, limit, startDate, and endDate including the exact-URL and no-null pitfalls. The description mostly repeats the URL-matching instruction rather than adding syntax or format meaning, so baseline 3 is appropriate.

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

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

The description names a specific verb and resource ('The Bing search queries that led to ONE landing page') and enumerates the returned metrics, then explicitly positions itself against sibling get_bing_page_stats as its 'natural drill-down'. An agent can distinguish this from get_bing_query_stats or get_bing_page_stats without opening any 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?

It gives clear context ('the natural drill-down after get_bing_page_stats') and a concrete prerequisite ('Pass the page URL exactly as get_bing_page_stats returns it'), which routes the agent correctly. It does not state when NOT to use it or name a competing per-page alternative, so it falls short of full when/when-not 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?

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that: it discloses the aggregation window semantics and, importantly, the notConfigured: true return when no Bing API key is set up, which is non-obvious failure behavior an agent should anticipate.

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

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

Two tight sentences with no filler. Purpose and scope are front-loaded, and the counterpart routing hint follows immediately, so the most decision-relevant information comes first.

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, the description need not explain return values, and it still covers purpose, scope, counterpart, and the key notConfigured error state. Only minor gaps remain, such as nothing on limit/ranking behavior, but those are handled by the 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 75% and the parameters (limit, startDate, endDate, siteUrl) are largely self-documented in the schema. The description only indirectly touches the window parameters via 'aggregated across the window' and adds no syntax or default guidance beyond the schema, so the 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?

States a specific resource (top landing pages on Bing Webmaster Tools) with explicit scope (aggregated across the window) and enumerates the metrics returned (clicks, impressions, CTR as 0-100 percentage, impression-weighted average position). It also positions itself against the sibling query_top_pages as the Bing counterpart, so an agent can route between Google and Bing data without opening either schema.

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

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

Naming query_top_pages as the counterpart implies when to reach for it (Bing instead of Google data), which is useful routing context. However, there is no explicit when-to-use/when-not statement or distinction from the other close Bing siblings such as get_bing_page_queries or get_bing_query_page_stats, leaving selection partly to inference.

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

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

Annotations cover safety (readOnly, non-destructive, openWorld), so the description earns credit by adding non-obvious behavior: the CTR scale is a 0-100 percentage, and the tool returns notConfigured: true when no Bing Webmaster key exists. That failure-mode disclosure is genuinely useful context 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?

Front-loads the returned metrics, then the differentiator, then parameter sourcing, then the edge case. Three tight sentences with no filler and no repetition of schema-declared facts.

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 shape need not be explained. The description still covers the key edge case (notConfigured), the distinguishing capability (pair-level position), and where to derive inputs, leaving nothing an agent needs to call it correctly.

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

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

Schema coverage is 80%, so structured fields already do most of the work (verbatim page/query, date omission behavior). The description still adds value by insisting query and page be taken verbatim from specific sibling endpoints, clarifying how to supply correct values rather than just what the fields are.

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 (daily clicks, impressions, CTR, average position) scoped to ONE exact query+landing-page pair on Bing. It also explicitly distinguishes itself from siblings as 'the only Bing endpoint that carries a true pair-level position,' so an agent can differentiate it from get_bing_query_page_stats or get_bing_page_queries without opening a schema.

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

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

Gives a concrete use case ('did this page slip for this term?') and tells the agent where to source required parameter values from (get_bing_query_page_stats / get_bing_page_queries). It stops short of stating when NOT to reach for it versus the sibling stats endpoints, but the intended context is 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 cover the safety profile (readOnly, non-destructive, open-world), and the description adds substantial context on top: aggregation across a window, CTR expressed as a 0-100 percentage, impression-weighted average position, the rowCount/totalRows distinction, and the notConfigured: true condition when no API key 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?

Front-loads the purpose, then metric details, then rowCount/totalRows semantics, then the notConfigured edge case. Every sentence carries information, though the three-sentence structure is slightly dense rather than maximally scannable.

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 windowed-stats read tool with a rich output schema and full annotation coverage, the description supplies everything an agent needs: scope, metric definitions, truncation semantics, and the no-API-key state. No material gap remains.

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 75% and the schema itself documents limit, startDate, and endDate thoroughly (format, defaults, 'never pass null'). The description adds only the limit-related rowCount semantics and the unset-API-key behavior, so it largely leaves parameter meaning to the schema — baseline 3.

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

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

Names a specific verb+resource ('top search queries on Bing Webmaster Tools for a property') and enumerates the metrics returned. It also explicitly positions itself as 'the Bing counterpart to query_top_queries', letting an agent distinguish it from the many sibling get_* stats tools without opening a 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 reference to query_top_queries gives a clear routing cue for when to pick this tool over the Google-side equivalent. It does not, however, state exclusions or contrast it with get_bing_keyword_stats / get_bing_query_page_stats, so it stops short of explicit when-not 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?

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the ~6-month data horizon and, importantly, that it returns notConfigured: true when no Bing API key is configured — a non-obvious failure mode the agent must anticipate.

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 compact sentences, front-loaded with purpose, then data scope, then the notable edge-case return. No filler, though the Google-comparison sentence is more contextual than essential.

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, return-value detail is unnecessary, and annotations carry the safety profile. The description supplies the data window and the notConfigured failure mode, leaving only minor gaps like auth requirements covered indirectly via openWorldHint.

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

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

Schema coverage is 67% and the startDate/endDate descriptions are already thorough (format, omit-both behavior, no-null warning). The description adds only "for a property" context and the 6-month default window; siteUrl itself is undocumented in both. Baseline 3 is appropriate given the schema does most of the work.

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

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

States a specific verb+resource: daily clicks and impressions from Bing Webmaster Tools for a property, and clarifies it covers Bing/Yahoo/DuckDuckGo organic. An agent can distinguish it from other Bing tools (crawl, query, page stats), though no sibling is named 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?

"Complements Google Search Console data with the Bing side of organic search" gives a reasonable context for when the tool is relevant, but there is no explicit when-to-use vs alternatives guidance or exclusions. Usage is implied rather than stated.

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

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

Annotations cover safety (readOnlyHint=true, openWorldHint=true), so the bar is lower. The description still adds real value by disclosing the notConfigured:true fallback when no API key exists, which is behavior an agent could not infer from annotations or schema. It doesn't mention rate limits or caching, but the key edge case is covered.

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

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

Two sentences, front-loaded with the core purpose and the return shape. Slightly redundant repetition of 'Bing Webmaster Tools URL-submission quota' across title and description, but no wasted clauses.

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

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

Output schema exists, so return-value structure needn't be explained. For a single-parameter read tool with full annotation coverage, the description adds the notConfigured edge case and the daily/monthly distinction, giving enough to call it correctly. Missing only the siteUrl format hint.

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?

One required parameter (siteUrl) at 0% schema description coverage, but zero parameters means baseline 4; with one parameter it drops to a 3. The description mentions 'for a property' which implies siteUrl maps to a property identifier, but gives no format, source, or validation guidance, and the schema provides only minLength:1.

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

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

States a specific verb-resource ('Remaining Bing Webmaster Tools URL-submission quota') and scopes it to a property. Distinguishes from siblings like get_inspection_quota (different engine) and submit_indexnow_urls (different submission path). An agent can identify the 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?

The description explains what the tool returns but never says when to call it, what triggers it, or how it relates to sibling tools such as submit_sitemap or get_crawl_stats. No alternatives are named and no conditions are given for selection.

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