Agentic Commerce Tools

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

With no annotations, the description carries the burden. It discloses that the tool returns a score (0-100), performs checks, returns itemized pass/fail results with fixes, and mentions rate limits and payment for high-volume calls. It also implies it makes HTTP requests to the target URL. It does not mention side effects or error handling, but given the nature, it covers the key behavioral aspects.

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 moderately long but every sentence adds value: purpose, checks performed, output, use cases, and pricing/rate limits. It is front-loaded with the core function and then provides supporting details. No filler or tautology, though it could be slightly shortened without losing essential 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?

Given the tool has a single parameter and no output schema, the description adequately explains what it does, what it checks, what it returns (itemized checks with pass/fail and fixes), and when to use it. It also addresses usage restrictions (rate limits, payment) and provides a link for production use. This is a complete description for a simple 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?

Schema description coverage is 100%, and the schema already explains the URL format and default scheme handling. The tool description does not add additional parameter details beyond restating the purpose. Per guidelines, the baseline is 3 when the schema covers parameters well; no extra value is added here.

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 a specific verb and resource: 'Score any website 0-100 on how ready it is for AI agents' and then lists concrete checks (robots.txt, llms.txt, structured data, etc.). This clearly distinguishes it from siblings like check_wellknown_discovery or generate_llms_txt by focusing on a holistic readiness score rather than a single file check.

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 use cases are provided: 'Use it to audit a merchant site, compare competitors, or generate an agentic-SEO to-do list.' It also gives practical guidance on rate limits (free tier self-limit) and alternative payment for high-volume use. It does not explicitly state when not to use it or name alternatives, but the context is clear enough.

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 full burden, and it does well: it discloses that the tool performs a real network handshake, checks live server endpoints, handles auth-protected servers, and provides scored results. It also mentions rate-limit expectations. It stops short of explaining any failure modes or side effects in more detail, but it is considerably more transparent than most.

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 longer than average but front-loaded and information-dense; each sentence adds purposeful context about behavior, use cases, or limits. The x402 payment and pricing details are somewhat promotional but still useful for high-volume usage guidance, so the length is justified.

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 having no output schema, the description comprehensively covers the returned score, letter grade, per-check breakdown fields, concrete fixes, auth-posture handling, and rate-limit expectations. Together with the single well-documented parameter, this makes the tool description complete enough for an agent to select and invoke it appropriately.

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 already documents the only parameter (url) with 100% coverage, including format, scheme-assumption, and private/localhost rejection. The description adds no new parameter-specific detail beyond restating 'streamable HTTP,' 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 opens with a specific verb and resource: 'Run a free, live health, conformance and latency scan of any remote MCP server.' It distinguishes itself from siblings by detailing the concrete JSON-RPC handshake, the 0-100 score letter grade, and the per-check breakdown, and by giving exact use cases like debugging why an agent platform rejects a server.

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 clear when-to-use guidance: 'Use it before recommending, installing or listing an MCP server, or to debug why an agent platform rejects one.' It also addresses volume constraints with the free-tier self-limit and the pay-per-call alternative, but it does not explicitly name sibling alternatives or state when not to use this tool.

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 full burden. It discloses the free tier, the six files checked, the return structure (score, per-file pass/warn/fail, generator links), and the rate limit plus paid option. No hidden side effects are implied; it is clearly a read-only audit.

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 paragraph but efficiently lists the six files, return values, and usage context. It is somewhat long but not padded; every sentence adds value. There is minor redundancy (e.g., 'and co.' could be replaced with full list) but structure flows logically.

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 and a single parameter, the description thoroughly explains what the tool returns (score, per-file status, generator links), when to use it, and the payment/rate-limit context. It is complete enough for an agent to decide and invoke without additional clues.

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% for the single 'url' parameter, so the schema already explains format and defaults. The description adds no extra parameter-specific meaning beyond the schema, meeting the baseline for full 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 audits a website's agent-discovery surface, enumerates the six specific files it checks, and contrasts with sibling agent_readiness_scan (page-level signals) making it distinct. The verb 'Audit' and resource 'agent-discovery surface' are specific and 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?

It explicitly states when to use: 'audit a merchant or SaaS site before agent integration, compare competitors' agent readiness, or produce a fix list.' It also differentiates from agent_readiness_scan and provides rate-limit guidance ('please self-limit to a few calls per minute') and alternative paid usage.

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 present, the description carries the full burden and succeeds well. It discloses the return shape (one paragraph plus canonical URL), unknown-term fallback behavior, input tolerance, offline snapshot execution with no network round-trip, and free/fair-use constraints. This is far richer behavioral disclosure than typical descriptions.

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 long, but the core purpose is front-loaded in the first sentence and subsequent sentences add genuinely useful details about coverage, matching, return value, and execution mode. The pricing and 'more agent tooling' sentence is somewhat tangential but not egregious.

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 tool with no output schema, this description is unusually complete. It covers the exact term list, matching rules, fallback behavior, response content, source URL, execution characteristics, and usage limits, making the tool independently understandable.

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 schema already describes case-insensitivity and separator tolerance. The description adds value by listing concrete example terms, naming the covered term categories, and explaining the unknown-term behavior that affects the single parameter's 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?

The description opens with a specific verb and resource: 'Look up a plain-English definition of any agentic-commerce, MCP, AI-visibility or agent-payments term from the Agent Glossary.' It clearly distinguishes the tool from sibling scanner/checker tools by framing it as a glossary lookup rather than a scanning or generation operation.

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 intended use case is clear: resolve glossary terms for agentic-commerce/MCP concepts. It does not explicitly name sibling alternatives or state when not to use them, but the lookup purpose is unambiguous and the sibling names make the division of labor obvious.

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 explicitly states 'Pure function: no network calls, deterministic, free, unlimited within fair use', covering side effects, determinism, and usage limits. It also discloses the output structure (ready-to-publish text plus metadata) and that it's spec-correct, going well beyond what annotations would 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 front-loaded with the core purpose and flow, but is somewhat long due to tangential mentions of Shopify and x402 promotions. While these add context, they dilute conciseness. Every sentence is purposeful but could be tightened; still, it's well-organized and readable.

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 compensates by fully describing the return format and metadata. It covers the tool's role in the ecosystem (checkers, AI-readiness), provides behavioral guarantees, and includes usage examples. It's comprehensive for a tool with 3 parameters, 100% schema coverage, and 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?

Schema coverage is 100%, so baseline is 3, but the description adds substantial meaning by mapping each parameter to its output role: summary becomes the blockquote, site_name the H1, and sections the H2s. It even explains the link bullet format, enriching the schema's descriptions with practical rendering context.

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 immediately states 'Generate a complete, spec-correct llms.txt file from structured input', with specific verb and resource. It explicitly identifies itself as the generator counterpart to this server's checkers, distinguishing it from sibling tools like agent_readiness_scan and check_wellknown_discovery.

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 says when to use: 'the generator counterpart to this server's checkers' and notes that AI-readiness scanners (including agent_readiness_scan and check_wellknown_discovery on this server) check for llms.txt, implying you use this tool first. It also explains how to serve the output. However, it doesn't explicitly state when NOT to use it or list alternative generators, so it lacks explicit 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 provided, so description carries full burden. It describes the return data (scores, grades, latency, aggregate stats) and mentions the underlying handshake. Implies read-only retrieval, though it does not explicitly state side effects or rate limits. Adequate but could be more explicit about non-destructive nature.

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?

Well-structured with clear sentences, but repeats 'Public MCP Server Index' and 'MCP' multiple times, adding slight redundancy. Still concise enough for the detail provided; could be tightened without losing 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?

No output schema is provided, but the description thoroughly explains the content of the index (per-server metrics, aggregate stats) and its use cases. It also notes the free nature and additional paid scanning service, covering practical context. Without parameters, this is 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?

Tool has zero parameters, so schema coverage is trivially 100%. Baseline for 0 params is 4; description notes 'no parameters,' which is sufficient. No additional parameter semantics needed.

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 it returns a Public MCP Server Index ranking servers by health, conformance, and latency. The purpose is unambiguous and distinct from sibling tools, mentioning the same handshake as check_mcp_server for context.

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 lists use cases: picking a reliable server, citing ecosystem statistics, and benchmarking. Also notes it is free and parameterless, which guides when to invoke it. Differentiates from server-specific 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?

No annotations are provided, so the description carries the full burden. It discloses that the data is fetched live server-side, is free, requires no auth, and is published by SellToAgents. It also describes the output contents (per-brand score, grade, failing checks, aggregate stats). It doesn't mention rate limits or caching behavior, but for a no-parameter read-only tool, the disclosure is quite thorough.

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 paragraph that front-loads the core purpose and then adds usage context and alternatives. It's longer than strictly necessary but every sentence adds value: the brand list, the checks, the use cases, the publisher, and the alternative tools. The structure could be improved with line breaks, but the content 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 zero-parameter, read-only tool with no output schema, the description is remarkably complete. It covers what the tool does, what it returns, when to use it, who publishes it, and how it relates to sibling tools. The only minor gap is not describing the exact output format (e.g., JSON structure), but the description's detail about per-brand scores, grades, and aggregate stats is sufficient for an agent to understand the return value.

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 has zero parameters, and the schema coverage is 100% (empty properties object). The description adds value by explaining what the tool returns and how it can be used, which is the relevant semantic context for a parameterless tool. A baseline of 4 is appropriate since there are no parameters to document.

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 returns the DTC AI Visibility Index, a recurring audit of well-known DTC brands scored 0-100 on AI-agent visibility. It specifies the exact checks (robots.txt, llms.txt, agents.md, structured data, meta quality, sitemap) and distinguishes it from sibling agent_readiness_scan by noting it uses the same checks but for a fixed brand list.

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 when to use this tool: to benchmark a merchant against named DTC brands, cite ecosystem statistics, or find outreach targets. It also explicitly names the alternative (agent_readiness_scan) for scoring arbitrary sites, and mentions the pay-per-call x402 API for high-volume pipelines, providing clear when-to-use vs when-not-to-use guidance.

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