Waitlist-stage pricing-page monitor: plans and early pricing, plus a PriceMovedBot robots.txt check.
Scored across 2 tools
The two tools have completely non-overlapping purposes: product_info returns static metadata about the service with no network calls, while robots_check performs a live RFC 9309 fetch for a given URL. An agent can trivially select the right one based on whether it needs service facts or a robots.txt verdict.
Both names use a consistent snake_case noun_verb/noun-topic style (product_info, robots_check) that is readable and predictable. No convention mixing is present.
Two tools is thin for a server whose stated domain is pricing-page change monitoring, though it plausibly reflects a waitlist-only product surface. It sits at the borderline of under-scoped rather than being badly matched.
The core domain — monitoring pricing pages and surfacing changes — has no tools at all; the surface exposes only service metadata and a robots.txt pre-check. There is no way to create, list, or retrieve monitoring targets or detected changes, leaving significant gaps for any real workflow.
Facts about PriceMoved, a pricing-page change monitor that is waitlist-only today: what is available now, the planned Free/Starter/Pro plans (pages, check intervals, Slack, history) with early USD prices that are subject to change, the crawler user agent, and links to the waitlist, privacy policy and terms. No network calls. Same data as GET /api/product.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| name | Yes | |
| links | Yes | |
| status | Yes | |
| contact | No | |
| crawler | No | |
| pricing | Yes | |
| summary | No | |
| version | Yes | |
| available_now | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real behavioral context: 'waitlist-only today', 'early USD prices that are subject to change', and 'No network calls'. Those tell the agent the data is a static snapshot that may go stale and requires no external fetch.
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?
Content is front-loaded with the subject ('Facts about PriceMoved...') and the parenthetical list efficiently packs the payload inventory rather than sprawling. The single dense sentence is slightly overloaded, and the trailing API-endpoint reference is marginal, but nothing is truly wasted.
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?
An output schema is present, so the description need not explain return values, and it duly focuses on scope and staleness caveats. For a zero-parameter, read-only info tool it is close to complete; the only omission is any hint about refresh/caching semantics beyond 'subject to change'.
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 per the rubric the baseline is 4. The description correctly adds nothing about arguments and instead spends its words on payload contents, which is the right allocation.
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 names the resource precisely and enumerates its payload (current availability, planned Free/Starter/Pro plans with page counts, check intervals, Slack, history, early USD prices, crawler user agent, policy links). That is far more specific than the title 'Product info'. It does not explicitly differentiate itself from the sibling robots_check, but the subject matter is self-evidently distinct.
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 clause 'Same data as GET /api/product' plus 'No network calls' implies this is a static-facts tool an agent should reach for when it needs plan/pricing details rather than live data. There is no explicit when-to-use or when-not-to-use statement and no alternative is named, so usage is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the robots.txt of the given public http(s) URL's site (at most 500 KiB, 5 s timeout, redirects followed) and report whether PriceMovedBot is allowed to fetch that URL under RFC 9309 rules: verdict allowed, disallowed, or skipped (robots.txt unreachable, 5xx/429, or too complex: PriceMoved would not fetch). Does not fetch the page itself. Domain names only (no IP addresses or ports). About 10 checks per minute and 30 per hour per network; results cached 10 minutes. Same engine as GET /api/robots-check.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL of the page, e.g. https://example.com/pricing |
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| note | Yes | |
| cached | Yes | |
| allowed | Yes | |
| verdict | Yes | |
| version | Yes | |
| checked_at | Yes | |
| robots_url | Yes | |
| user_agent | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds substantial behavior beyond annotations: 500 KiB size cap, 5 s timeout, redirect handling, RFC 9309 rules, exact verdict semantics including skipped cases, rate limits of 10/min and 30/hour per network, and a 10-minute cache. These details materially affect invocation and result interpretation.
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?
Dense but front-loaded: it starts with the core action and verdict, then adds limits, exclusions, rate limits, and caching. Every sentence contributes operational information without redundancy.
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?
Complete for this tool: output schema exists so return values need not be explained, and the description covers scope, constraints, failure modes, rate limits, and caching. An agent has enough information to 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%, so the URL parameter is already documented. The description nonetheless adds useful semantics: it must be a public http(s) URL, the check applies to the URL's site, and IP addresses and ports are not allowed.
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: fetch robots.txt for the given URL's site and report whether PriceMovedBot may fetch that URL. It clearly distinguishes the operation from fetching the page itself and names the exact verdicts returned.
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?
Provides clear context for when the tool applies, including the exclusions that it checks robots.txt rather than the page and only accepts domain names, not IPs or ports. It does not name explicit alternative tools, but none of the listed siblings compete with this purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
product_inforobots_checkCheck AI crawler robots.txt policy and monitor public-site policy, sitemap, and llms.txt changes.
Check AI crawler robots.txt policy and monitor public-site policy, sitemap, and llms.txt changes.
Extract and structure pricing pages from any SaaS site: plans, tiers, and features.
Recurring webpage change, price, inventory and metadata monitoring for autonomous agents.
Add one secure layer between your agents and this server.