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

With no annotations provided, the description carries the full burden. It explains dedup logic (keeps highest severity per entity), severity thresholds (critical > warning), and warns against speculation. However, it does not disclose authentication needs, rate limits, or 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 description is concise with two short paragraphs. The core purpose is front-loaded in the first sentence, and the crucial usage note is highlighted separately. No unnecessary repetition.

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 complexity (3 parameters, no output schema), the description adequately covers purpose and behavior but lacks return value structure. It does not specify what the output looks like beyond 'emits per-entity alerts', which may leave gaps for an AI 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 coverage is 0%, so the description must add meaning. It explains the 'days' parameter via 'last N days vs prior N days' and mentions severity threshold. However, 'site_url' is only indirectly explained via 'per-entity (query+page)', and no details on input format or constraints are given.

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 detects regressions by comparing last N days to prior N days, and lists specific alert types (position_drop, ctr_collapse, click_drop, disappeared) and severity levels. This distinguishes it from siblings like traffic_drops.

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 includes an important usage note about not speculating beyond returned data, but it does not provide explicit guidance on when to use this tool versus alternatives like traffic_drops or content_decay. The context of per-entity alerts is implied but not contrasted.

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

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

No annotations are provided, so the description must disclose behavioral traits. It implies read-only behavior by instructing to use only returned data, but does not explicitly state it is safe, nor does it mention authorization needs, rate limits, or output format.

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 sentences with a critical note. It is front-loaded with the main purpose and the note earns its place by preventing misuse. 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?

Despite 4 parameters and no output schema, the description fails to explain the output format, how to interpret results, or detailed usage. The note is helpful but insufficient for an agent to correctly invoke and handle the tool.

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

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

With 0% schema description coverage, the description must explain parameters. It only mentions site_url and date_range in the note, but does not describe days, min_impressions, or top_n. The description adds minimal value 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?

The description clearly states the tool identifies queries where multiple pages compete. It uses a specific verb and resource, but does not explicitly differentiate from sibling tools like content_decay or traffic_drops.

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 IMPORTANT note provides guidance on using only returned data and citing site_url + date_range, which gives context for reporting. However, it does not specify when to use this tool versus alternatives or preconditions.

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

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

With no annotations, the description carries the transparency burden. It explains the algorithmic filter (monotonic decline over 3 windows, threshold). It does not disclose auth requirements, rate limits, or whether the tool is read-only. The logic is fairly transparent but lacks some behavioral details.

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 brief and to the point: first sentence states purpose, second elaborates on criteria, third gives an important usage warning. No fluff. Information is front-loaded.

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

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

Given the lack of output schema and annotations, the description covers the core logic and usage caveats. However, it does not explain the output format, pagination, or error cases. For a simple list tool, it is adequate but could be more 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 has 3 parameters (site_url, top_n, min_clicks_p3) with 0% description coverage. The description mentions 'clicks_p3 >= threshold' but does not explicitly map threshold to min_clicks_p3 or explain top_n. The names are somewhat self-explanatory, but the description adds minimal 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 finds pages with monotonic decline across 3 consecutive 30-day windows, indicating real content decay. It explains the filtering criteria, distinguishing it from random dips. However, it lacks an explicit verb like 'list' or 'find', and could be more direct.

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 context for when to use the tool: to detect genuine content decay, not single-week dips. It includes a warning against speculation and extrapolation, guiding proper usage. However, it does not explicitly mention when not to use or compare with sibling tools like traffic_drops.

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

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

No annotations are provided, so the description must disclose behavioral traits. It explains the metric calculation and warns against speculation, but it does not mention that the tool is read-only, any rate limits, or what happens with insufficient data. It also does not describe the output format or any 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 description is concise, consisting of three sentences. The first sentence states the purpose, the second defines the metric, and the third provides an important usage guideline. It is front-loaded and each sentence adds value, though the warning is slightly longer.

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 4 parameters and no output schema or annotations, the description should provide a more complete picture. It defines the core metric but fails to describe parameter roles, output structure, or thresholds for 'significantly below'. The tool's complexity is moderate, and the description leaves 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 schema coverage is 0%, meaning the description must compensate for missing parameter documentation. However, the description does not explain any of the four parameters (site_url, days, min_impressions, top_n). It only implies 'site_url' and 'date_range' in the note, but without explicit mapping to parameters. This is a significant omission.

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

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

The description clearly identifies the tool's purpose: listing pages with CTR significantly below expected for their position, and defines the CTR gap metric. It is specific and distinguishes from siblings like search_analytics, though no explicit verb like 'list' or 'retrieve' is used.

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 includes a strong 'IMPORTANT' note instructing the agent to use only the returned data and to cite site_url and date_range. This provides some guidance, but it does not specify when to use this tool versus alternatives such as 'search_analytics' or 'quick_wins', nor does it mention exclusions.

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

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

With no annotations, description fully discloses behavior: lists tools and checks credentials. It notes 'quick check' implying speed, and mentions grouping by category. Does not mention rate limits or output size, but adequate for a simple discovery tool.

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

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

Two concise sentences front-loaded with key 'Call FIRST'. Every word adds value 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?

Given no parameters, no output schema, and simple purpose, the description is fully complete. It explains what, when, and what it returns, fitting well with sibling tools that are action-specific.

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?

No parameters, schema coverage 100%, so description adds no parameter info. Baseline for 0 parameters is 4, which 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?

Description clearly states it lists all tools exposed by the MCP and current auth status, using specific verb 'List' and resource 'tools'. It also includes 'Call FIRST' as a directive, distinguishing it from sibling tools as a discovery tool.

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

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

Explicitly says 'Call FIRST', providing clear guidance on when to use it. It explains the return value includes tool catalog grouped by category and auth status, indirectly suggesting it's for initial orientation, not for specific actions like siblings.

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

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

No annotations exist, so the description carries the full burden. It describes the tool as inspecting a URL (presumably read-only) but doesn't explicitly state nondestructive behavior, rate limits, or auth needs. The warning about data usage adds some transparency.

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 a clear purpose line, structured Args section, and an important usage note. Every part earns its place without redundancy.

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

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

Given no output schema, the description enumerates return values (indexing status, last-crawl, etc.) and covers all parameters. The warning completes the guidance for downstream use.

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 0% schema coverage, the description adds crucial details: site_url format (including sc-domain), page_url must belong to site_url, and language default (en-US). This significantly augments the bare 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 the action ('Inspect a single URL against Google's index') and lists the returned data types (indexing status, last-crawl, etc.), distinguishing it from sibling tools like search_analytics or list_sitemaps.

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 explicit warnings about using only returned data and not extrapolating, and instructs to cite site_url + date_range. However, it does not compare to alternatives or say when not to use.

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

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

No annotations are provided, so the description carries full burden. It warns against speculation and instructs citing site_url+date_range, but does not disclose whether the tool has side effects, authentication requirements, rate limits, or the nature of the output (e.g., only new sitemaps, etc.). The mention of date_range is confusing since the input only has site_url.

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 sentences: the first states purpose, the second gives an important usage constraint. It is efficient and front-loaded, with 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 the tool has one required parameter, no output schema, and no annotations, the description should be more thorough. It does not explain what the returned data looks like, whether it is paginated, or if there are limits. The warning is about data usage, not about the tool's overall behavior.

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

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

Schema description coverage is 0%, meaning the parameter site_url has no description in the schema. The description does not explain what site_url is (it only says 'for a property'), nor does it provide format or constraints. It adds minimal value 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?

The description starts with 'List sitemaps submitted for a property, with errors/warnings/last-submitted info,' which is a specific verb+resource. It clearly distinguishes from sibling tools like list_sites (lists sites) and submit_sitemap (submits a sitemap).

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

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

The description includes an important warning about using only returned data and citing site_url+date_range, but it does not explicitly state when to use this tool versus alternatives, nor when not to use it. Usage is implied but not guided.

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

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

No annotations provided, so description carries full burden. It discloses return fields but does not mention side effects, rate limits, or authentication specifics. For a read-only listing, this is adequate but not exceptional.

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: purpose, output description, and usage caution. No wasted words, front-loaded with main action.

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 no parameters and no output schema, the description fully covers the tool's behavior, output, and usage constraints. Complete for its simplicity.

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?

No parameters exist, so baseline is 4. Description adds meaning by specifying return fields, which is beneficial beyond the empty 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 the tool lists all Search Console properties the user has access to, with specific output fields. It does not explicitly distinguish from siblings but the purpose is direct.

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 includes an 'IMPORTANT' note instructing the agent to use only the returned data, not speculate, and cite site_url and date_range. This provides concrete usage guidance.

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

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

No annotations are provided, so the description carries the full burden. It transparently explains the opportunity score formula and gives caveats about not speculating. However, it does not disclose if the tool is read-only or any authentication requirements, which is acceptable for a query tool.

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

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

The description is concise at five sentences, front-loaded with purpose and formula, followed by an important usage note. Every sentence adds value with zero redundancy.

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

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

Given no output schema, the description hints at return structure (queries with opportunity scores) but lacks details on fields, sorting, or pagination. It is adequate for a simple tool but could be more complete, especially covering parameter roles.

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

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

Schema description coverage is 0%, yet the description provides no explanation of any parameter (site_url, days, min_impressions, top_n). The description focuses entirely on output semantics, leaving the agent without guidance on how to set input 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 clearly states the tool queries queries ranking 4-15 with highest lift opportunity and explains the scoring formula. While it distinguishes the tool's purpose, it does not explicitly differentiate it from sibling tools like 'ctr_opportunities' or 'content_decay'.

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 includes an IMPORTANT note restricting use of data, which provides some guidance. However, it does not specify when to use this tool versus alternatives, leaving the usage context 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?

With no annotations, the description must fully disclose behaviors. It explicitly states that the tool 'Does not delete files; just resets in-process clients,' clarifying safety. It also explains the effect ('force re-authentication on the next API call') and the mechanism ('resets in-process clients'). This is comprehensive for a simple tool.

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

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

The description is extremely concise: three sentences with no superfluous words. The first sentence immediately states the core action. Every sentence adds necessary information—purpose, conditions, and behavioral note—making it highly efficient.

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 no parameters, no output schema, and a simple action, the description covers all essential aspects: what it does, when to use it, and what it does not do. It is fully self-contained and leaves no ambiguity for an AI agent to invoke the tool correctly.

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

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

There are no parameters, so the schema coverage is trivially 100%. The description adds value beyond the schema by explaining the tool's purpose and side effects. Per guidelines, zero parameters defaults to a baseline of 4, but the description's extra context (when to use, behavioral details) raises it to a 5.

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 function: 'Force re-authentication on the next API call.' It uses a specific verb ('force re-authentication') and resource (API call), making the purpose unambiguous. It also implicitly distinguishes from sibling tools by focusing on authentication, a unique capability among the listed siblings.

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 use cases: 'when ADC credentials have changed or OAuth token has expired and cached state is stale.' This tells the agent exactly when to employ the tool, offering clear context. Although it doesn't list when not to use it, the positive conditions are sufficiently specific.

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

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

No annotations are provided, so the description carries the full burden. It explains parameters and mentions a server-side cap (25000) for row_limit. However, it does not disclose whether the tool is read-only or rate limits.

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

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

The description is concise and uses newlines to separate the overview, parameter list, and important note. It could be more structured (e.g., bullet points) but remains efficient and front-loads the 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?

Covers all 6 parameters with examples and crucial usage guidelines. However, since no output schema exists, the description omits the return format, which could be inferred but is not explicit.

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

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

Schema description coverage is 0%, and the description fully compensates by explaining each parameter: site_url as 'Property URL', date range as 'ISO YYYY-MM-DD', dimensions with examples, row_limit cap, and search_type values.

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 performs a 'Custom Search Analytics query' for Google Search Console data, with specific parameters. However, it does not distinguish itself from sibling tools like 'alerts' or 'cannibalization', which could cause confusion.

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?

Includes an important note instructing users to only use returned data and cite site_url and date_range, providing clear usage context. Does not explicitly state when not to use the tool or mention 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?

No annotations are provided, so the description must cover behavioral traits. It states the tool returns aggregated totals for a current period versus a prior period, and warns against extrapolation. However, it does not disclose whether the data accounts for any filtering (e.g., device, country), how the prior period is calculated, or any limitations like data freshness or sampling. The warning about not speculating adds some transparency, but overall more detail would be beneficial.

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 extremely concise: two sentences, each serving a purpose. The first sentence states the function clearly, and the second provides critical usage instructions. No unnecessary words, and the key information is front-loaded.

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

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

Given 2 parameters, no output schema, and sibling tools that also provide performance data, the description is moderately complete. It names the metrics returned but not the structure (e.g., whether it's a single object or array). The tool's output is a simple aggregated comparison, so a detailed return format may not be critical, but the lack of explanation of the prior period's calculation leaves a 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?

With 0% schema description coverage, the description must compensate. It mentions 'last N days' which implies the 'days' parameter, but does not explicitly define the 'site_url' parameter or clarify the format or constraints. The prior period is not explained (e.g., same length preceding period). The description adds minimal meaning beyond what the schema provides (parameter names and types).

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 provides aggregated totals (clicks, impressions, CTR, position) for the last N days compared to a prior period. It identifies the resource (site's performance data) and the action (aggregation and comparison). While it does not explicitly distinguish from sibling tools like search_analytics, the focus on aggregated totals vs prior period makes its purpose reasonably distinct.

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 guidance on not speculating beyond the returned data and citing site_url and date_range when reporting. However, it lacks guidance on when to use this tool versus alternative tools (e.g., search_analytics for granular data, or cannibalization for specific insights). There is no mention of prerequisites or context where this tool is preferred.

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

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

No annotations are provided, so the description must carry the full burden. It notes the destructive nature via the prerequisite flag and includes an instruction not to speculate on results, but it lacks details on success/failure behavior, side effects, or rate limits.

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

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

The description is highly concise: two short paragraphs covering purpose, parameters, a requirement, and a behavioral note. Every sentence adds value 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?

Given the tool has only two parameters and no output schema, the description covers purpose, parameter meanings, a usage condition, and a behavioral instruction. It lacks details on return value, but this is acceptable for a simple submission 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?

The schema coverage is 0%, but the description adds meaning by defining 'site_url' as 'Property URL' and 'feedpath' as 'Full sitemap URL' with an example. This compensates somewhat for the lack of schema descriptions.

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 'Submit a sitemap' with a specific verb and resource. It distinguishes from sibling tool 'list_sitemaps' which lists sitemaps, making the action 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 mentions the prerequisite 'GSC_ALLOW_DESTRUCTIVE=true', which provides necessary context but does not explicitly state when to use this tool versus alternatives or when not to use it.

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 discloses the classification logic with specific thresholds and warns about speculation. However, with no annotations, it fails to describe other behaviors like read-only nature, rate limits, or output structure. The note about citing site_url and date_range is helpful but partial.

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 efficient, front-loading the main purpose, using bullet points for classifications, and a concise note. Every sentence adds value without redundancy.

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

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

Despite clear purpose, the description is incomplete for a tool with 4 parameters and no output schema. It lacks explanation of parameter effects, return format, and behavior over time (e.g., how days combine). The note about using only returned data is good but insufficient for correct invocation.

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

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

The description adds no semantics for the parameters beyond what the schema shows. It mentions site_url and date_range in the note but does not explain the meaning of 'days', 'top_n', or 'min_clicks_prior'. With 0% schema coverage, the description should compensate but does not.

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 it identifies 'Pages that lost traffic' and classifies them into three specific types (Ranking-loss, CTR-collapse, Demand-decline) with precise thresholds. This distinguishes it from sibling tools like 'search_analytics' and 'content_decay'.

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 instructs to 'Use ONLY the data returned by this tool' and warns against speculation, providing clear usage context. However, it does not explicitly compare against alternatives or state when not to use it.

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