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

With no annotations, the description carries the burden and does well by disclosing the static nature, the 30-resource limit, and capped/guarded requests. It doesn't mention exact output format or edge cases, but overall provides meaningful behavioral context beyond the schema.

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 concise, information-dense sentences with no fluff. It front-loads the core purpose and adds key constraints efficiently.

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

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

For a simple 1-parameter tool with no output schema, the description adequately explains what is measured, resource categories, and limits. Return values are implied by 'counts and byte sizes', though nesting or exact response structure isn't specified. This is sufficient given the tool's 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?

The input schema has 100% coverage for the single 'url' parameter with a clear description. The tool description adds no additional parameter-specific semantics, 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?

The description clearly states the tool performs static page-weight analysis, enumerating specific resource categories (scripts, stylesheets, images, fonts, iframes) and largest third-party scripts. This distinguishes it from sibling tools like measure_performance or audit_page.

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

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

The description implies usage for static resource-size analysis but does not explicitly state when to prefer it over alternatives or when not to use it. The cap of 30 resources hints at lightweight use, but no exclusions or comparisons are provided.

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 adds important behavioral context: 'Fast (no browser)' conveys the non-browser, lightweight nature, and 'single readable report' indicates output format. It does not detail limitations or error cases, but the provided traits are valuable for tool selection.

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, front-loaded with the core function, and every sentence earns its place. It is concise, well-structured, and avoids unnecessary details.

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

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

For a one-parameter tool with no output schema, the description is complete: it lists the audit areas, states the output format, and clarifies how it differs from key sibling tools. The guidance is sufficient for an agent to select and invoke it correctly.

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

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

Schema coverage is 100% for the single required url parameter, so the schema already explains it. The description adds no extra parameter semantics beyond referencing 'URL', which is redundant with 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?

The description clearly defines the tool as a one-shot URL audit covering tracking tags, duplicate-tag risks, header hygiene, and resource counts. It distinguishes itself from sibling tools by naming specific alternatives for byte-level weight and lab Core Web Vitals.

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

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

The description gives explicit guidance on when to use this tool (one-shot comprehensive audit) and points to alternatives: 'For byte-level page weight use analyze_page_weight; for lab Core Web Vitals use measure_performance.' This is clear and practical.

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

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

The description adds useful behavioral context by stating 'Informational grades with explanations, no synthetic scores,' disclosing the nature of the output and that it does not produce synthetic scores. Yet, with no annotations provided, it does not fully offset the burden: it fails to mention network-side effects (e.g., it makes a request), error handling, or any authorization requirements, which are relevant for a tool that fetches URLs.

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, the first listing the scope of inspection and the second clarifying the output style. Every word earns its place, and there is no redundancy or 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?

Given the simplicity of the tool (one parameter, no output schema), the description is largely complete: it states the purpose, the categories of headers analyzed, and the output format (grades with explanations). It lacks explicit notes on network behavior or edge cases, but these are not critical for a simple header-checking tool, and the output description compensates partially for the missing 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?

The schema already fully describes the only parameter (url) with a clear format and example. The description does not add new semantic details about the parameter beyond what the schema provides, so the baseline of 3 is appropriate given the 100% schema coverage.

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

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

The description clearly states the tool's function with a specific verb ('Inspect') and resource ('the page's HTTP response headers'), and it enumerates the specific headers it analyzes (caching, HSTS, CSP, etc.). This distinguishes it from sibling tools like 'measure_performance' or 'detect_tracking_tags', which focus on different aspects of a page.

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

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

The description implies usage context by listing the types of headers it checks (security, caching, CDN), which suggests it is used to audit these specific aspects. However, it does not explicitly state when to use this tool over alternatives or provide any exclusionary guidance, leaving the agent to infer the appropriate scenario.

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

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

With no annotations provided, the description carries the transparency burden. It discloses the 'static scan' nature (not rendering JS) and the output format ('reports IDs and where each was found'). It does not mention potential fetch behavior, rate limits, or failure modes, but the key behavioral trait is sufficiently conveyed.

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, front-loaded with the action and scope. The enumerated list of tag types is detailed but directly relevant, and the second sentence crisp describes output. No filler or redundant information.

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

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

For a one-parameter tool without an output schema, the description sufficiently covers what it does, the method (static), and the output. It lacks detail on edge cases like redirects or dynamic content, but the 'static' qualifier preemptively clarifies limitations. Given the tool's simplicity, the description is nearly 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?

The only parameter (url) is fully described in the schema with a clear example, so schema coverage is 100%. The description adds no further parameter-specific detail, which is acceptable as the schema already provides adequate semantics. Baseline 3 applies.

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

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

The description clearly states a specific action ('static scan') on a specific resource ('page's HTML') for a well-defined purpose (detecting analytics/advertising tags). The explicit list of supported tags and output details (IDs and locations) distinguishes it from sibling tools like find_duplicate_tags or tracking_summary.

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

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

The description implies when to use the tool—when you need to detect tracking tags in a page's static HTML. However, it provides no explicit guidance on when not to use it or how it compares to alternatives such as find_duplicate_tags or tracking_summary, leaving the choice to the agent.

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 carry the full behavioral burden. It uses the verb 'flag', which suggests a read-only audit, and lists specific patterns it detects. However, it does not explicitly state that the tool is non-destructive, what permissions/authentication might be needed, whether it fetches the URL, or what the output format looks like. The lack of explicit disclosure for a read-only tool is a minor gap.

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

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

The description is a single, information-dense sentence that front-loads the action and then lists concrete examples of duplicate patterns. Every part adds value, with no filler or repetition, making it concise and well-structured.

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

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

The tool is simple (one parameter, no output schema), and the description explains the types of issues it surfaces comprehensively. However, it does not specify what the tool returns (e.g., a list, count, or report), which would be helpful given there is no output schema. Overall, it is mostly complete for the tool's complexity.

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

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

The input schema provides a complete description for the single 'url' parameter (100% coverage), so the schema already carries the parameter documentation. The tool description does not add any extra meaning about how the URL is used or any additional parameter constraints, so the baseline score of 3 is appropriate.

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

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

The description clearly states the tool's purpose with a specific verb ('Flag') and resource ('duplicate GA4/GTM/pixel installations and double-fire patterns'). It enumerates concrete examples of what it detects, effectively distinguishing it from sibling tools like detect_tracking_tags, which likely identify any tags, and tracking_summary, which likely aggregates tag data.

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

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

The description implies the tool is for finding duplicate tag setups, but it does not explicitly state when to use it versus alternatives (e.g., 'use this when checking for double-firing, otherwise use detect_tracking_tags'). No 'when-not' or alternative references are given, so usage is only inferred from the content.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It explains that Playwright is required, that the tool returns an install command if missing, and that the data is lab data. This gives useful context beyond the basic action, though it does not cover every possible behavior like output format 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 two sentences long, front-loaded with the action, and every sentence adds value without redundancy. It is concise yet comprehensive for its scope.

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 single parameter and no output schema, the description is fairly complete: it names the metrics captured, the dependency, and the failure mode. However, it does not describe the exact return format on success, which would be helpful since there is no output 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?

The schema description covers 100% of the single parameter (url) with type and example. The description adds no extra parameter-level meaning, 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?

The description uses a specific verb ('Load the page... and capture') with a clear resource and explicit list of metrics (TTFB, FCP, LCP, CLS, load times, request count, transfer sizes). This distinguishes it from sibling tools like analyze_page_weight or check_headers.

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 clarifies this returns lab data, not field data, and states the prerequisite of the Playwright Chromium browser. However, it does not name alternative sibling tools or explicitly state when to use this tool over them, so it stops 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?

No annotations are provided, so the description carries the transparency burden. It clearly discloses the output's content and perspective (plain-language, marketing-focused) and mentions surfacing issues for the dev team. It does not state whether the tool performs a live fetch or side effects, but 'summary' strongly implies a read-only operation.

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

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

One sentence with a colon-separated list packs high information density without fluff. It is front-loaded with the key purpose and intended audience.

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 one-parameter tool, the description fully explains the deliverable and topics covered. It lacks return-format details and usage timing, but those are partially covered by the simple parameter and sibling context, making it adequate though not exhaustive.

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 a single parameter and 100% schema coverage, the schema already defines 'url' as an absolute http(s) URL to audit. The tool description itself adds no further parameter-level detail, which is acceptable given the schema's completeness.

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 opens with 'Plain-language summary' naming the deliverable and audience (media buyer/marketer), and enumerates content areas: installed tracking, campaign implications, consent posture, and dev-team issues. This clearly distinguishes it from sibling tag-detection or performance-audit tools by its synthesizing role.

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

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

No explicit when-to-use or when-not-to-use is stated, nor are alternative tools named. The audience and purpose are clear enough to imply use when a non-technical, synthesized summary is needed, but there is no exclusion guidance against using related tools like detect_tracking_tags.

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