HubVibe Site Audits

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

The description adds important behavioral details beyond the annotations: atomicity (any failure causes whole call to fail and nothing billed) and the $0.10 per call cost. It also specifies the return structure (pass bool plus sub-results). These are not present in the annotations, which only cover read-only and idempotent hints. No contradiction.

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 four sentences, each conveying essential information: the scope, atomicity, pricing, and return format. It is front-loaded with the primary purpose and does not waste 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?

The description is complete given the tool's complexity: it explains the atomic behavior, cost, and return structure. An output schema exists, so return values are further specified. No critical information is missing for an agent to decide whether to use it.

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%, with the url parameter already described as 'Live, fetchable http(s) URL to audit.' The tool description does not provide additional parameter-specific information, so it meets the baseline for high 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 runs all four audits (wcag, seo, security, performance) against one URL, distinguishing it from the individual sibling tools. The verb 'runs' is specific and the scope 'against one URL' is explicit.

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 context is clear: this is the combined bundle for all four audits, implied by 'all four audits' and 'billed as a single call.' However, it does not explicitly state when to prefer individual tools over the bundle, so it lacks explicit when-not/alternatives 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, idempotentHint=true, and destructiveHint=false, covering safety. The description adds value beyond annotations by revealing that the tool performs a real page load (a behavioral trait likely to have network side-effects), discloses the cost ($0.03 per call), and summarizes the return structure (pass, metrics{}, findings[]), which is not redundant given the output schema exists but is not shown to the model.

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 compact: two sentences that front-load the key deliverables (metrics and return format) and the qualification ('not a full Lighthouse audit'). The cost is stated succinctly. No filler words or redundant phrases. Slightly more could be trimmed (e.g., the return summary could be dropped if output schema is visible), but overall it is 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?

For a simple read-only tool with one parameter, the description covers the essentials: what it measures, the nature of the operation (real page load), the cost, and the return shape. Nothing critical is missing for an agent to decide whether to call it. It does not address rate limits or potential failures, but those are not implied by annotations or schema, and the tool is straightforward.

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', has a schema description that fully covers its meaning and format ('Live, fetchable http(s) URL to audit'). The tool description adds marginal context by noting the page load is 'real', which reinforces the 'live' nature, but essentially replicates the schema. With 100% schema coverage, 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 ('audit') and resource ('page performance'), enumerates concrete metrics (DOM node count, transferred bytes, request count), and explicitly contrasts with a full Lighthouse audit. This clarifies scope and differentiates from the concept of a comprehensive audit, though it doesn't name sibling tools 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?

The description implies this is a lightweight, focused performance check ('not a full Lighthouse audit') and notes a per-call cost, suggesting it is for quick spot-checks. However, it does not explicitly state when to prefer this over sibling tools like audit_bundle or audit_security, nor does it provide any exclusion criteria.

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

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

Annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds valuable behavioral context beyond the annotations: the call makes a live HTTP request (network dependency), costs $0.03 per call, and returns a specific shape (pass bool and findings[] with id/severity/detail). This is more than the annotations alone provide.

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 dense sentence front-loaded with the key scope, followed by an exclusion, cost, and return summary. Every element earns its place; there is no filler or repetition of schema data.

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

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

With an output schema present and one fully documented parameter, the description is complete for practical use. It tells the agent exactly what is checked, what is not, what it costs, and what the response contains, leaving no meaningful gap 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 schema already fully documents the single parameter with description and format, and schema coverage is 100%, so the baseline of 3 applies. The description adds no additional semantic detail about the url parameter beyond what the schema provides, but it doesn't need to.

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 action verb with a clear resource: auditing security headers from a live HTTP response. It enumerates the exact checks (HTTPS, HSTS, CSP, X-Content-Type-Options, clickjacking, Referrer-Policy, CORS) and explicitly excludes TLS/cipher scans and penetration tests, making it easy to distinguish from the other audit 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 clearly says what the tool covers and explicitly states what it does not cover ('not a TLS/cipher scan or a penetration test'), which is useful when-routing guidance. It does not name sibling tools directly, but the listed checks leave little doubt about when this should be selected over audit_performance, audit_seo, or audit_wcag.

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, idempotentHint=true, and openWorldHint=true, so the safety profile is covered. The description adds valuable behavioral details beyond annotations: the per-call cost ($0.03) and the precise return format (pass bool, findings[] with id/severity/detail). No contradictions exist.

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, efficient sentence that front-loads the audit targets, then lists cost and returns. No fluff, but it could be slightly more structured (e.g., separating input modes from return structure). Still concise and skimmable.

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

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

With an output schema available (signal indicates has output schema: true) and annotations covering safety, the description provides enough operational details: inputs, cost, and return shape. It omits any edge-case caveats (e.g., what happens if URL fetch fails), but for a read-only audit this is acceptable given the surrounding context.

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 both parameters (url and html) are already documented with clear descriptions. The tool description adds no additional parameter-specific meaning, meeting the baseline for high 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 explicitly lists the SEO elements audited (title, meta description, H1, canonical, OpenGraph, structured data, lang) and names the return structure (pass bool, findings[]). This clearly distinguishes it from sibling audit tools (performance, security, WCAG, bundle) which target different concerns.

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 specifies the two input modes (url vs html) and implies use for SEO checks, but gives no explicit guidance on when to prefer this tool over siblings or when not to use it. The 'when' is left to the agent's inference from the name and listed checks.

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, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds value by disclosing the cost ('$0.03 per call') and the precise return structure (pass bool, violations with id/impact/help/help_url/nodes_affected), which are not covered by annotations or the output schema alone.

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 three concise sentences: purpose, cost, and return format. It is front-loaded with the core purpose and contains no redundant or filler text.

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 (accepts url or html), has a full output schema, and the description covers cost and return format. Annotations cover read-only, idempotency, and non-destructive behavior. Nothing critical is missing for an agent to call this 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?

Schema coverage is 100%, with both 'url' and 'html' parameters clearly described. The tool description does not add extra parameter-specific semantics beyond what the schema already provides, so the baseline score of 3 applies when the schema handles parameter documentation.

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

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

The description opens with 'WCAG 2.1 A/AA accessibility audit via axe-core,' specifying the exact domain (accessibility), standard (WCAG 2.1 A/AA), and engine (axe-core). This clearly distinguishes it from sibling tools like audit_performance, audit_security, etc., which target different audit types.

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 states what the tool does but gives no explicit guidance on when to use it over alternatives or when it should not be used. The usage context (accessibility auditing) is implied by the name and description, but no exclusions or references to sibling tools are provided.

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