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

With no annotations, the description carries the full burden. It discloses that the url is fetched server-side and returns viewport flags, issues list, and mobile score. It does not mention whether it is read-only or any side effects, but the audit nature implies non-destructiveness.

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, front-loaded with purpose, followed by inputs and outputs. 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?

For a simple two-parameter tool with no output schema, the description covers purpose, inputs, and output types. It could add more detail on outputs (e.g., format of issues list) or constraints (e.g., url accessibility), but overall it's fairly 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 coverage is 0%, so the description compensates by explaining that url is for a live URL fetched server-side and html is for raw HTML. This adds meaning beyond schema types. However, it could clarify that exactly one must be provided (implied by 'OR' but not explicit).

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 the specific verb 'audit' and clearly identifies the resource: 'viewport meta and horizontal-scroll risk on mobile'. This clearly distinguishes it from sibling tools like audit_speed or check_links.

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 states inputs: 'Pass a live url (fetched server-side) OR a raw html string', giving clear guidance on how to use it. However, it does not explicitly state when not to use it or provide alternatives, though the context of siblings implies it's for mobile-specific issues.

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 present, so the description carries full burden. It mentions the URL is fetched server-side and lists return fields, but fails to disclose whether the tool is read-only, destructive, or has any side effects, rate limits, or authentication requirements.

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 uses simple formatting with backticks for code. It front-loads the purpose and provides essential input/output info without unnecessary 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 no output schema, the description adequately lists return fields (html_bytes, render-blocking scripts, etc.). It covers the two input modes and their behavior. A minor gap: it doesn't specify if both parameters can be omitted or if exactly one is required.

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 compensates by explaining that 'url' is fetched server-side and 'html' is a raw string. This adds basic meaning beyond the schema, but lacks details on valid formats, constraints, or whether both can be provided simultaneously.

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 audits static load-speed signals from HTML, using a verb ('Audit') and a specific resource ('load-speed signals'). It differentiates from siblings like audit_mobile or check_links by focusing on speed, but does not explicitly contrast with them.

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 that you can pass a live URL (fetched server-side) or a raw HTML string, giving clear context on input options. However, it does not provide guidance on when to use this tool versus alternatives like audit_mobile or score_page, nor does it mention any prerequisites or 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?

No annotations are provided, so the description carries full burden. It discloses that the tool fetches server-side for URLs and returns a structured result including counts and a has_broken flag. It does not mention side effects, but as a read-only check, this 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?

The description is concise with two clear sentences: first states purpose, second explains usage. No filler, every sentence adds value.

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 low complexity (2 optional parameters, no output schema, no nested objects), the description covers the tool's purpose, input options, and return fields completely. No additional context is needed.

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

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

With 0% schema description coverage, the description adds essential meaning: 'url' is live and fetched server-side, 'html' is raw string. However, it does not detail constraints like valid URL schemes or HTML encoding, leaving some ambiguity.

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

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

Description clearly states 'Check internal and outbound links for broken HTTP status codes', using a specific verb and resource. It distinguishes from sibling tools like audit_mobile or cta_clarity, which focus on other aspects.

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?

Description provides clear guidance on how to use the tool: 'Pass a live url (fetched server-side) OR a raw html string.' It explains the two input options but does not explicitly state when not to use this tool or mention alternatives, though it's implicit from sibling names.

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 fully convey behavioral traits. It only lists return fields and describes a read-like analysis, but omits details on whether the url fetch is destructive, authentication needs, or rate limits. This leaves the agent with insufficient behavioral context.

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—three sentences—with the purpose front-loaded. Every sentence adds value: what it does, how to call it, and what it returns. No unnecessary 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 no output schema and low parameter complexity, the description covers key returns and inputs. However, it omits details like required inputs (one of url/html), behavior when both are provided, and error handling. The contextual completeness is adequate but not comprehensive.

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

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

With 0% schema description coverage, the description adds essential meaning: it explains that url is fetched server-side and html is raw, and that either can be passed. This goes beyond the schema's anyOf and null defaults, making parameter usage clear.

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 analyzes CTA presence, count, and above-the-fold placement, using a specific verb-resource pair. It distinguishes from sibling tools like audit_mobile or check_links by focusing on CTA elements.

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

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

The description explains the two input options (url or html) but does not provide guidance on when to use this tool versus siblings (e.g., audit_mobile for mobile-specific CTA). Without exclusions or alternative references, the usage context is only partially 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?

No annotations are provided, so the description bears full responsibility. It discloses that the URL is fetched server-side and describes the output (booleans, list, count). However, it does not specify behavior when both url and html are provided, error handling, 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?

Three concise sentences: first states purpose, second explains input options, third describes output. No redundancy, every sentence adds value.

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

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

Given the tool's simplicity (2 optional params, no output schema, no annotations), the description covers input options and output structure. Could be improved by specifying behavior when both params are provided or neither, but it's sufficient 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?

Schema coverage is 0%, so the description adds essential meaning: url is a 'live url (fetched server-side)' and html is a 'raw html string'. This clarifies the difference and usage mode beyond the raw schema which only lists types and defaults.

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 verb (detect) and the resource (specific tracking pixels: Meta Pixel, GA4, GTM, TikTok). It distinguishes itself from sibling tools like audit_mobile and audit_speed by focusing on pixel detection.

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

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

Explicit guidance on using either a URL or raw HTML string, which covers the primary usage scenario. No explicit when-not-to-use or alternative suggestions, but the context signals show sibling tools cover different domains, implying this tool is for pixel detection only.

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 of behavioral disclosure. It describes the tool's behavior: it fetches the URL server-side or uses the provided HTML, then returns a verdict and related data. However, the phrase 'Block ad spend' might be interpreted as the tool actually executing a blocking action, while the output suggests it only returns analysis. This ambiguity reduces transparency, but the description does clarify the analytical nature by listing return fields.

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 covering what the tool does, how to use it (inputs), and what it returns (outputs). No redundant information, and the key details are front-loaded. Every sentence adds meaningful value.

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 4 parameters (two undocumented), no output schema, and no annotations, the description should be more comprehensive. While it does list return fields, it lacks details on parameter constraints (e.g., URL format, HTML structure), dependencies, or error conditions. For a tool that potentially impacts ad spend, more behavioral and usage context would be beneficial.

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 4 parameters with 0% description coverage, meaning no parameter descriptions exist in the schema. The description mentions 'url' and 'html' but does not explain 'platform' or 'platform_csv', leaving nearly half the parameters undocumented. This fails to compensate for the lack of schema descriptions, making it harder for the agent to use the tool correctly.

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: 'Block ad spend on leaky landing pages.' It specifies the action (block ad spend) and the resource (landing pages). The distinction from sibling tools like audit_mobile and audit_speed is evident because those are audit-focused, while this tool is about spend blocking. The description also lists key inputs (url or html) and outputs.

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

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

The description provides explicit usage instructions: 'Pass a live url (fetched server-side) OR a raw html string.' It also lists the return values, helping the agent understand what to expect. However, it does not explicitly mention when not to use this tool or compare it to siblings, though the sibling tools are sufficiently different that no further guidance is needed.

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

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

No annotations are provided, so the description must carry the full burden. It discloses the mock nature and path to live, but omits details about error behavior, rate limits, or side effects. This is acceptable but leaves gaps.

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, well-structured sentence that conveys the core purpose and a key usage note. No unnecessary words, and the critical 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 no output schema, no annotations, and incomplete parameter documentation, the description does not sufficiently explain what metrics are returned or how to use the parameter. It is too brief for a complete understanding.

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 one required 'platform' parameter with 0% schema description coverage. The description does not explain what values are valid or how they affect output, failing to add meaning 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 action ('Return') and the resource ('mock ad-platform campaign metrics'), and distinguishes itself from sibling tools which focus on audits and other checks. It also hints at transitioning to live usage with real API keys.

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 mock data and suggests upgrading to live by plugging in API keys. While it doesn't explicitly list alternatives, the context of mock vs. live is clear, and sibling tools have different purposes, so guidance is adequate.

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 burden. Discloses return fields (grade, score, signals, spend_at_risk, details) but omits side effects, auth, 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?

Two sentences plus a return line. Front-loaded with main purpose. 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?

Covers main functionality, parameters, and return types. Lacks error conditions or limitations but sufficient for a straightforward scoring tool without 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?

Schema coverage is 0%, so description must compensate. Explains url and html are mutually exclusive, and verbose is boolean, but does not specify format or constraints. Vague on verbose effect.

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

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

Clearly states verb 'score', resource 'landing page', and output 'A-F grade with per-signal breakdown'. Differentiates from sibling tools like audit_mobile and audit_speed.

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 when to use (pass url or html) but does not explicitly state when not to use or compare to alternatives. Usage context is implied but lacks exclusions.

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