agent-site-audit - website audits for agents

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

With no annotations, the description carries the full burden and does well: it discloses that the tool is paid (0.25 USDC on Base via x402), what the unpaid call returns, and the exact signing/retry protocol. It does not cover rate limits, idempotency, or whether repeated audits are cached, which are minor residual 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?

Two dense sentences with the price and scope front-loaded and no filler. The output enumeration is long but each item is informative, so it stays within reason rather than padding.

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

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

No output schema exists, but the description compensates by listing the flat-JSON return fields, and no annotations means the payment/safety behavior is explicitly covered. The one missing piece is sibling differentiation against deep_audit and scan_site.

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 already 100%, so the baseline is 3, and the description adds real meaning by explaining the two-phase protocol for the 'payment' parameter (omit on first call, pass the challenge response on retry) that the schema only hints at.

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

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

States a specific verb+resource ('Full deterministic website audit') and enumerates the concrete outputs (HTTP status, latency, robots policy, redirect chain, issue list, 0-100 score), so an agent knows exactly what it gets. It does not differentiate itself from the siblings deep_audit or scan_site, so it falls short of a 5.

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?

It clearly describes the call flow: call without payment to receive the x402 challenge, then retry with a signed EIP-3009 authorization in the 'payment' argument. However, it gives no guidance on when to prefer this over deep_audit or scan_site, which is the main alternative-selection question an agent faces here.

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 full burden and does disclose the most important behavioral trait: this is a paid tool requiring 0.25 USDC on Base via x402, and it returns a report_url alongside the JSON. It stops short of describing the payment handshake failure mode (e.g. a 402 challenge when the payment payload is missing) or any latency/rate limits, so it is strong but not complete.

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?

Front-loaded with the cost and the output format, then the audit scope, then the fix/remediation deliverable, then report_url. Dense but every clause conveys distinct information. The single long enumerated sentence is heavy but not padded.

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?

There is no output schema, so the description must describe returns, and it does so thoroughly (finding severities, copy-paste fixes, prioritised remediation plan, HTML report URL). Combined with the explicit payment terms, an agent has nearly everything needed. The missing piece is sibling positioning and payment failure behaviour.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning to the 'payment' parameter by naming the price, currency, and rail (0.25 USDC on Base via x402), which is what an agent needs to construct the payload. The 'url' parameter is fully covered by 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?

States a specific verb and resource ('Technical deep audit as JSON') and enumerates the exact audit scope: TLS, security headers, cookie flags, DNS/email security, compression/caching, AI-agent readiness. An agent knows precisely what comes back. It does not, however, differentiate itself from the siblings audit_site, scan_site, or service_info, which prevents a 5.

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

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

Usage is only implied: the 'deep' framing and the price signal (0.25 USDC) suggest this is the heavyweight, paid option versus a lighter sibling scan. There is no explicit when-to-use, when-not-to-use, or named alternative, so the agent must infer selection from the name and cost alone.

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 full burden and does disclose the key behavioral traits: this is a free, partial scan (only 3 of 9 checks) whose result is a sample of a paid product, and it returns JSON. Auth requirements, rate limits, and whether the URL is fetched live are left unstated, keeping it below a 5.

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

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

Two tight sentences, front-loaded with the free-preview framing and the check breakdown, with no filler. "Returns JSON" is justified because there is no output schema.

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 single-parameter, no-output-schema read tool, the description conveys the scope limit and return format adequately. Return-value structure is only named, not detailed, but the absence of an output schema makes that a minor gap.

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

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

Schema coverage is 100% and the single url parameter is fully documented in the schema, so the baseline is 3. The description lists what gets checked but adds no new meaning about the parameter itself (format, constraints, redirect handling).

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 concrete verb+resource (free preview of a website audit) and scopes it precisely as 3 of 9 checks, which implicitly separates it from the full-audit siblings audit_site/deep_audit. It does not name those siblings, so the differentiation is inferable rather than 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?

"Use it to see the shape of the result before paying" gives a clear usage condition (pre-purchase exploration) that routes the agent away from a full audit. It stops short of naming the paid alternative or stating exclusions, so it is clear context without explicit 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?

With no annotations, the description carries the full burden, and it delivers the key traits: the call is free, the service is paid, and payment is x402 with USDC on Base. It does not spell out auth requirements or that the tool is read-only, but for a zero-parameter info endpoint that omits little of practical consequence.

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

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

Three short sentences, front-loaded with the cost profile ('Free.') and the routing instruction ('Call this first'). Every clause adds information; there is no filler or restatement of the name.

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?

There is no output schema, but the description enumerates the returned content (products, prices, payment instructions), which compensates. For a simple, parameterless info tool with no annotations this is close to complete; only auth/rate-limit behavior is unaddressed.

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 tool takes zero parameters, so there is no syntax to document and the baseline of 4 applies. The description correctly spends no words on inputs.

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

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

States a specific verb and resource ('Describes this paid website-audit service') and enumerates exactly what it returns: the three products, their prices, and the x402 payment procedure. An agent cannot confuse this informational tool with the audit siblings (audit_site, deep_audit, scan_site), whose names imply performing an audit rather than describing the service.

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?

It gives an explicit trigger: 'Call this first if you do not know how to pay', which implies the negative case (skip it when you already know how to pay). It does not name the sibling tools or state conditions for choosing among the audits, but the routing guidance for this tool itself is clear.

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