Traffic exchange network for independent websites. Without a key: network size, member sites, membership check and exchange rules. With a personal key from the BarterBanner dashboard: your sites, campaigns, view reports, widget code — and, if the key allows, creating campaigns.
Scored across 4 tools
Each tool targets a clearly distinct need: checking a single site, explaining network rules, listing all members, and reporting aggregate stats. The overlap between check_site and list_members is only apparent, since one is a targeted lookup and the other is a full listing.
All names use snake_case, which is consistent, but the naming pattern is mixed: check_site and list_members are verb_noun, while how_it_works and network_stats are descriptive phrases rather than verb_noun tools. The set remains readable, though not fully predictable.
Four tools is well-scoped for a focused public showcase/network information server. Each tool covers a distinct informational area, and none feels redundant or excessive.
The surface covers checking a site, understanding the rules, listing members, and viewing network stats, which addresses the core read-only domain. Minor gaps include no dedicated member-detail lookup or search/filter operation, but agents can work around these via list_members.
Checks whether a website is in the BarterBanner public showcase. Accepts a bare domain or a URL. If the site is not listed, returns how to join.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | domain or URL of the website, e.g. example.com |
| Name | Required | Description |
|---|---|---|
| note | Yes | |
| title | No | title of the site's card, if a member |
| domain | Yes | the domain as it was checked, without scheme or www |
| member | Yes | |
| join_url | Yes | |
| link_url | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly, idempotent, and closed-world safety, so the bar is lower. The description adds real behavioral context beyond the annotations: accepted input forms and the not-listed branch that returns joining instructions. It stops short of richer disclosure such as lookup-scope limits or error behavior.
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: purpose first, input forms second, edge-case outcome last. No filler, and the most decision-relevant 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?
An output schema exists so return values need no explanation, and annotations cover the safety profile. The description covers the one behavioral branch that matters (unlisted site), leaving nothing an agent needs to invoke this single-parameter 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?
There is one parameter at 100% schema coverage, and the schema already documents it as 'domain or URL of the website, e.g. example.com'. The description restates the accepted formats without adding normalization rules, validation constraints, or format specifics, so it does not exceed 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?
Specific verb+resource: it checks whether a given website is in the BarterBanner public showcase, which an agent can distinguish from list_members (enumerate) and network_stats (aggregate). It does not explicitly name a sibling or contrast itself with one, so clarity is strong but not maximally differentiated.
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 accepted input (a bare domain or URL) signals when the tool applies, but the description never states when to prefer it over list_members or how_it_works, nor any exclusions. Adequate but leaves routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The rules of the exchange as the network actually computes them: what a view earns, what counts as a view, the commission, the welcome credits, and how to install the widget.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| free | Yes | |
| summary | Yes | |
| commission | Yes | share of each paid view kept by the network |
| moderation | Yes | |
| register_url | Yes | |
| earn_per_view | Yes | |
| quality_range | Yes | lowest and highest price of one view, in credits |
| widget_formats | Yes | |
| widget_snippet | Yes | |
| welcome_credits | Yes | credits granted when the domain is verified |
| welcome_matched | Yes | further credits, granted as the site earns its own |
| what_counts_as_a_view | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so safety and determinism are covered. The description adds one useful nuance — these are the rules "as the network actually computes them," i.e. de facto behavior rather than advertised policy — but says nothing further about freshness, caching, or authority of the content.
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?
A single front-loaded sentence that defines the resource first and then lists the topics covered. Every clause earns its place, and there is no filler or 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?
With no parameters and an output schema present, the description need not explain return values and correctly focuses on scope. It is complete enough for correct invocation, though stating that the returned rules are authoritative/current would close the last 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?
The tool takes no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. Schema coverage is 100% with additionalProperties=false, so the empty input contract is fully unambiguous.
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 (the exchange's rules) and enumerates the specific contents returned: view earnings, view definition, commission, welcome credits, and widget installation. The verb is implicit ("returns/shows") and the tool name alone (how_it_works) would be opaque, but the enumerated scope lets an agent distinguish it from check_site, list_members, and network_stats.
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 implied — an agent reads this when it needs the exchange's rules — but there is no explicit when-to-use or when-not statement, and no routing to or away from the sibling tools. Adequate but leaves selection to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Websites in the network, one card per site, as shown in the public showcase on the BarterBanner home page: domain, the card's title and description, and where it links. Paused members are included — the showcase lists who is in the network, not who is serving today.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| members | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already cover the safety profile (readOnly, idempotent, closed-world), but the description adds a genuinely useful behavioral note beyond them: paused members are still included, with the rationale that the showcase lists membership rather than current serving status. Minor gaps remain — no ordering or size/scale expectation for the list.
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, front-loaded with the resource being listed and with the paused-members caveat given its own emphasized clause. Slightly dense in the first sentence's field enumeration, but nothing is wasted or repeated from structured fields.
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 exists so the return shape need not be explained, and the annotations carry the safety profile. What the description adds — the showcase semantics and paused-member inclusion — is the meaningful remaining context. It could go one step further and state what callers should use instead when they want active-serving sites only.
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 parameter semantics for the description to add; the baseline for a parameterless tool applies. The stated 'one card per site' also implicitly guarantees no pagination or filter arguments exist.
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 concrete resource — websites in the network, one card per site — and enumerates the card's fields (domain, title, description, link target). It is clear what an agent gets back, but it never names or contrasts itself with siblings like network_stats or check_site, so an agent must infer the boundary.
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 'public showcase on the BarterBanner home page' framing tells an agent this is the read path for viewing who is in the network. There is no explicit when-to-use statement, no exclusions, and no routing guidance against check_site or network_stats.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Current size of the BarterBanner network: verified active member sites, active member campaigns, and card impressions over the last 7 days. Figures are refreshed every few minutes.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| as_of | Yes | time of this answer, UTC, RFC 3339 |
| sites | Yes | verified, active member sites |
| campaigns | Yes | active member campaigns (platform promos excluded) |
| impressions_week | Yes | card impressions recorded over the last 7 days |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly, idempotent, and closed-world behavior, so the description is not required to cover safety. It adds genuinely new operational context: the 7-day measurement window and a refresh cadence of 'every few minutes', which tells the agent the figures are near-real-time rather than a historical archive.
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 short sentences, front-loaded with what is returned and followed by the freshness caveat. Every clause carries information; nothing is redundant with the name, title, or annotations.
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 exists, so return structure need not be described. Combined with annotations covering the safety profile, the description supplies the remaining essentials: metric definitions and data recency. Only the when-to-use routing is left implicit.
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 no parameters, so the baseline is 4. The description correctly uses its space to define the data scope (7-day window, 'verified active') instead of inventing parameter semantics that don't exist.
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 ('BarterBanner network') and the three specific metrics returned (active member sites, active member campaigns, card impressions), which is enough for an agent to distinguish it from list_members or check_site. It lacks an explicit verb like 'retrieve', but the content is 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?
There is no guidance on when to call this versus the sibling tools (check_site, list_members, how_it_works), nor any stated preconditions. The agent must infer that this is the aggregate-stats entry point from the description alone.
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.
check_sitehow_it_workslist_membersnetwork_statsFree anonymous website, DNS, email and TLS checks, plus monitor read and opt-in write access.
Real-time web analytics for AI agents: query traffic, funnels, revenue, and manage your sites.
Free AI-visibility and competitive Exposure Audit for any domain. No account, no API key.
Privacy-first, cookie-free web analytics: create sites, install and verify tracking, read stats.
Add one secure layer between your agents and this server.
