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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: the scoring methodology (estimated additional clicks assuming a 10% CTR) and the impression/position gating, which tells the agent how rows are ranked and why some data is absent.

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

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

Three sentences, front-loaded with what is found, then the ranking basis, then the use case — no filler. Minor imprecision in calling the results 'Suchanfragen' before clarifying they are query+page combinations, but the structure is efficient overall.

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 read-only, zero-required-parameter tool with fully documented schema, the description covers purpose, filtering logic, ranking, and use case. With no output schema, it could say a bit more about the shape of returned rows (which columns the agent will see), which is the only real 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 the schema already documents all six parameters including defaults and bounds. The description only restates the band (8–20) and the impression threshold conceptually; it adds no syntax, format, or interaction detail beyond the schema. 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: it finds query+page combinations in a defined striking-distance band (positions 8–20) with sufficient impressions, and it discloses the sort order (estimated extra clicks at 10% CTR). The query+page granularity and the position band distinguish it from the broader sibling gsc_suchanfragen without needing to name 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?

Gives a concrete decision scenario — 'Ideal, um zu entscheiden, welche Seiten zuerst überarbeitet werden' — which tells the agent when this output is the right input for prioritization. It stops short of naming alternatives or exclusion conditions (e.g. when to use gsc_suchanfragen instead), so it is clear context without full routing guidance.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description usefully adds that results include impressions, CTR and average position, but says nothing about ordering guarantees, result limits, or how the default property (GSC_PROPERTY) is resolved.

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

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

A single front-loaded sentence that states resource, ranking basis and returned metrics with no filler. It is efficient, though it spends its only sentence on output content rather than routing guidance.

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 low-complexity, fully-optional-parameter, read-only tool with 100% schema coverage and no output schema, the description covers what an agent needs: what the rows are and which metrics come back. Only the missing sibling routing and ordering behavior keep it from being complete.

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

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

Schema description coverage is 100%: all three parameters (tage, limit, property) are fully documented in the schema, including defaults and bounds. The description adds no parameter-level detail, so the 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 ("Liefert") and resource ("Seiten einer Google-Search-Console-Property"), plus the ranking criterion ("mit den meisten Klicks") and the metrics returned. It is clearly distinct in content from a query-level tool, but it never names or contrasts with the sibling gsc_suchanfragen, so sibling differentiation is left implicit.

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

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

The phrase "mit den meisten Klicks" implies this is the tool for a top-pages-by-clicks report, which is usable guidance by implication. However, there is no explicit when-to-use statement, no mention of when to prefer gsc_suchanfragen or gsc_fast_seite_eins, and no prerequisites (e.g. that a property must be configured).

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 declare readOnlyHint=true and openWorldHint=true, so safety and external data source are already covered. The description adds that results are sorted by clicks and include specific metrics, which is useful context. However, it doesn't mention pagination limits, data freshness beyond what the schema says, or what happens if the property is invalid. With annotations covering the safety profile, a 3 is appropriate.

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

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

One sentence, front-loaded with the core action, no wasted words. Efficient and clear.

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 the essential purpose and metrics. For a read-only analytics tool with fully documented parameters and annotations, it is nearly complete. It could mention that results are limited by default (25 rows) or how to interpret average position, but these are minor given the schema covers limits.

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

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

Schema description coverage is 100%, so all three parameters (tage, limit, property) are fully documented in the schema itself. The description adds no additional parameter meaning, such as timezone or date-range nuances. Baseline 3 is correct when the schema does the heavy lifting.

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

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

States a specific verb+resource: returns top search queries for a GSC property, listing the metrics (clicks, impressions, CTR, position) and the sort order. Clear for an agent. It doesn't explicitly distinguish itself from sibling gsc_seiten (likely top pages), but the 'Suchanfragen' (queries) focus is evident.

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?

Implied usage: query analytics data for a property. No explicit when-to-use or when-not-to-use guidance, and siblings like gsc_seiten (pages) are not referenced or contrasted. An agent must infer that this tool is for query-level data rather than page-level.

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 declare readOnlyHint=true and openWorldHint=true, and the description adds meaningful context beyond them: the URL Inspection API, the inspected fields, and the requirement that the service account needs full access in the property. It does not describe quota/rate-limit behavior, but the auth and return-scope disclosure is valuable.

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 front-loaded sentences with no wasted wording. It first states the action and inspected result dimensions, then states the access prerequisite.

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

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

With no output schema, the description usefully enumerates the main returned inspection fields, and annotations cover the safety profile. It includes the important auth prerequisite, though it could say more about error cases or quota constraints for a live URL Inspection API call.

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

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

Schema description coverage is 100%, so the schema already documents url, sprache, and property in detail. The description adds no parameter-specific syntax or format guidance beyond implying a single URL and referencing property access, so the 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 states a specific verb and resource: 'Prüft eine einzelne URL über die URL Inspection API' and lists inspected aspects. It implicitly distinguishes this single-URL inspection from sibling list/report tools, though it does not name those alternatives 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?

Usage is implied by 'eine einzelne URL' and the URL Inspection API context, but the description gives no explicit when-to-use/when-not guidance or alternatives among siblings such as gsc_suchanfragen or gsc_seiten. The access prerequisite is stated, but not routing guidance.

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

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

Adds important behavioral context beyond the annotations: the requirement that the key file be reachable at a specific URL pattern, and that key/host can come from environment variables. This complements the openWorldHint and idempotentHint annotations. It does not detail error behavior or rate limits, but the key-file prerequisite is a notable addition.

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 core action and recipients. Every sentence carries necessary information about inputs, defaults, and the key-file prerequisite, 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?

Complete for a submission tool with no output schema: covers what it does, how to provide URLs, default sources for key/host, and the critical external requirement of the key file. Nothing an agent needs to call it correctly is missing.

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

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

Schema coverage is 100%, so the schema already documents all five parameters with defaults. The description mentions key and host sources and the key file location, but adds only marginal detail beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

States a specific verb (meldet) and resource (neue oder geänderte URLs) and names the target services (Bing, Yandex, weitere Suchmaschinen). Clearly distinguishes from siblings like gsc_url_pruefen and gsc_suchanfragen, which concern Google Search Console checks rather than IndexNow submission to multiple engines.

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 that URLs can be submitted directly or via a sitemap, which is a clear usage instruction. It does not explicitly state when to prefer this tool over siblings like gsc_fast_seite_eins, but the context is sufficient for selection.

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 and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context: it loads a page over the network, requires no credentials, and returns a finding plus a shortening hint. It stops short of mentioning rate limits or error behavior, so it is not 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 short sentences, front-loaded with the action 'Lädt eine Seite...', with no wasted clauses. Each sentence carries distinct information: what is loaded and checked, the exact thresholds and return values, and that no credentials are 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?

No output schema exists, so the description appropriately sketches return values ('Befund und einen Kürzungshinweis'). Combined with 100% parameter coverage and annotations, an agent has enough to invoke and interpret the tool, though the exact format of the 'Befund' remains unspecified.

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 (url) with 100% schema description coverage, so the schema already fully documents the parameter. The description's length thresholds describe the check performed on the page content rather than the meaning of the url parameter, so it adds nothing beyond the structured field.

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: loads a page, reads title and meta description, and checks lengths against specific thresholds (title max 60, meta description 70–155 characters). It is clearly about meta-length auditing rather than GSC data or indexing, but it does not explicitly name or distinguish itself from siblings like gsc_url_pruefen or gsc_fast_seite_eins.

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 contextual guidance that the limits are stricter Bing limits that also suit Google, implying use for SEO meta checks, but it never states when to choose this tool over alternatives or when not to use it. No sibling tool is referenced, so the agent must infer the intended workflow.

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