The first commercial implementation of HTTP 402 Payment Required for creator content monetization. AI agents pay $0.0025 per content pull from paywalled creator libraries. Patent-pending micropayment infrastructure — creators get paid automatically.
Scored across 3 tools
list_pockets and search_pockets both return pocket rows and could be confused at a glance, but the descriptions explicitly route the agent ("prefer search_pockets for specific topics", "do NOT use for browsing"), and pull_content is clearly a separate retrieval action. Boundaries are effectively taught, just not self-evident from names alone.
All three names follow a clean snake_case verb_noun pattern: list_pockets, search_pockets, pull_content. The verb choice also maps to intent (discovery verbs vs. a retrieval verb), so the naming reinforces the mental model rather than fighting it.
Three tools is on the thin side, but for a content catalog the minimum viable surface really is browse, search, and fetch, and each tool has a distinct job. Nothing redundant, though there is little headroom if the domain grows (accounts, receipts, licensing).
Discovery (list/search) and delivery (pull) are covered end-to-end, but there is no way to inspect a single pocket's metadata by pocket_id without triggering a metered pull, and no tools for account/balance, registration, or receipt verification even though the descriptions reference all of these. These gaps will force agents into blind or costly calls.
List all available content pockets in the Meta-Stamp Pockets catalog, optionally filtered by creator. Use this tool when an AI agent needs to browse the full catalog or see everything available from a specific creator. Prefer search_pockets when looking for specific topics. Does NOT retrieve content — use pull_content with the returned pocket_id to access actual content. Works without authentication; anonymous results omit content_url and creator_id, which are returned only with a valid Bearer token (pkt_ API key). The optional creator_id parameter filters results to a single creator's pockets and requires an API key (anonymous calls using it are refused with an api_key_required error and a registration_url). Returns a paginated list of pockets with IDs, titles, descriptions, creators, content types, and pricing tiers. Each row also carries catalog_id, access ('open' or 'closed') and delivery ('file' or 'listing'); closed-catalog and listing rows never include content_url. Unlisted pockets are never listed; they stay reachable by pocket_id (pull_content) or by an exact isrc in search_pockets.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return per page. Defaults to 50, maximum 200 for catalog browsing. | |
| creator_id | No | Optional filter to show only pockets from a specific creator. Use the creator's unique identifier. Requires an API key; refused for anonymous callers. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and delivers: anonymous calls work but omit content_url/creator_id, the creator_id filter requires a Bearer token (pkt_ API key) and fails anonymously with api_key_required plus a registration_url, results are paginated, and closed-catalog/listing rows never include content_url. It also discloses that unlisted pockets are never returned but remain reachable by pocket_id or exact isrc.
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?
Purpose and routing are front-loaded in the first sentences, and nearly every sentence adds a distinct constraint that an agent needs. It runs long and repeats the creator_id API-key requirement already in the schema, which slightly dilutes it, but there is little true filler.
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 output schema, the description compensates by enumerating the returned fields (IDs, titles, descriptions, creators, content types, pricing tiers) plus catalog_id, access, and delivery semantics. Combined with auth and pagination notes, an agent has everything needed to call and interpret this 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%, so both parameters are already documented. The description reinforces creator_id's API-key requirement and its refusal behavior, which the schema mentions more briefly, but adds no syntax, format, or edge-case detail for limit beyond what the schema states. Baseline 3 applies.
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 ('List all available content pockets in the Meta-Stamp Pockets catalog') and immediately names its scope ('optionally filtered by creator'). It explicitly distinguishes itself from both siblings by calling out that it does not retrieve content and by naming search_pockets for topic search.
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?
Gives explicit when-to-use ('browse the full catalog or see everything available from a specific creator'), names the alternative with its selecting condition ('Prefer search_pockets when looking for specific topics'), and routes content access to pull_content with the returned pocket_id. Exclusions are stated rather than inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pull licensed creator content from a specific pocket by ID. Use this tool when an AI agent needs to retrieve verified, provenance-tracked content for generation, RAG, and inference use. Training use requires a separate training license — see training_use in the agreement terms. Do NOT use for browsing or discovery — use search_pockets or list_pockets instead. Requires a valid Bearer token for authentication; unauthenticated requests return HTTP 402. Successful pulls trigger a metered charge at the pocket's own price (quoted as owner_price on the receipt; $0.0025 platform default only when a pocket sets none) and the transaction is logged for creator royalty distribution. The pocket_id parameter is a 24-character hex string identifying the specific content pocket to pull from. Returns the full content payload with provenance metadata including creator attribution and license terms. Every call returns a receipt of the same shape (receipt_id, outcome, reason, amount_paid, terms, content_hash, and agent_count / agent_work_count: how many times this agent has accessed the owner's account and this work, this call included) with a public verify_url: on success under 'receipt' in the result (outcome 'delivered'), on an HTTP 402 refusal under 'receipt' in the error body (outcome 'refused', reason 'registration_required' when no valid API key is presented, 'payment_required' when the wallet balance is too low or the card charge fails). A pocket whose rights holder has closed its catalog is refused for every caller, with or without a key, as a normal result (not a 402) with reason 'catalog_closed', owner_price null and the receipt under 'receipt'; nothing is delivered or charged. A listing-only pocket (delivery 'listing' in search results) has no file: its pull is charged the owner's per-pull price like any other and returns delivery 'listing' with 'content' set to the listing object {title, isrc, owner, terms, link} and no download URL. content_hash is the sha256 hex of the delivered 'content' field only: a string is hashed as its UTF-8 bytes, an object as UTF-8 JSON with sorted keys and no whitespace.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Optional natural language focus query used to narrow or contextualize the returned content within the selected pocket. | |
| pocket_id | Yes | The 24-character hex identifier of the content pocket to pull from. Obtain this from search_pockets or list_pockets results. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description carries the full burden: Bearer token auth with HTTP 402 on failure, metered per-pull charging with owner_price vs platform default, royalty logging, the full receipt taxonomy including refused/catalog_closed outcomes, and listing-only pocket behavior. This is exactly the behavioral context an agent needs before incurring a charge.
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?
Purpose and usage are correctly front-loaded, but the second half is a dense wall of run-on sentences packing receipt shapes, error outcome enums, and the content_hash algorithm into unstructured prose. The content is substantive, but the delivery is hard to parse and would improve as a short structured list.
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 output schema, the description fully documents return values: provenance metadata, receipt fields, verify_url placement on success vs 402 error bodies, and the content_hash computation. For a paid, auth-gated tool, nothing an agent needs to call or interpret results is missing.
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. The description restates pocket_id as a 24-character hex string (already in the schema) and never mentions the optional 'query' parameter, so it adds little semantic value beyond structured fields.
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+scope: 'Pull licensed creator content from a specific pocket by ID.' It also names the sibling tools it is not ('Do NOT use for browsing or discovery — use search_pockets or list_pockets instead'), so an agent can route correctly without comparing schemas.
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 states the use case (retrieval of verified, provenance-tracked content for generation, RAG, inference), the exclusion (browsing/discovery), the named alternatives, and the licensing boundary (training requires a separate license).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Meta-Stamp Pockets catalog by keyword, creator email, or content category. Use this tool when an AI agent needs to discover available licensed content before pulling it. Ideal for finding relevant pockets when the agent knows what topic or creator it needs but not the specific pocket ID. Does NOT retrieve content — use pull_content with the returned pocket_id to access actual content. Works without authentication for query, isrc and content_type; anonymous results omit content_url and creator_id, which are returned only with a valid Bearer token (pkt_ API key). The query parameter is matched as a literal keyword and accepts natural language search terms or category keywords; the creator_email parameter restricts results to a single creator by their email address and requires an API key (anonymous calls using it are refused with an api_key_required error and a registration_url). The isrc parameter is an exact full-ISRC lookup. Provide at least one of query, creator_email or isrc. Returns matching pockets with their IDs, titles, descriptions, creators, content types, and pricing tiers. Each row also carries catalog_id, access ('open' or 'closed') and delivery ('file' or 'listing'). Closed-catalog rows cannot be pulled and never include content_url; listing rows show title, isrc and owner and never include content_url. Unlisted pockets are excluded from results unless found by an exact isrc match. Use the limit parameter to control page size.
| Name | Required | Description | Default |
|---|---|---|---|
| isrc | No | Optional exact ISRC lookup: the full 12-character code, dashes allowed (e.g. 'USRC17607839' or 'US-RC1-76-07839'). Matches case- and dash-insensitively; a partial ISRC is rejected. This is the only search that also returns unlisted pockets. | |
| limit | No | Maximum number of results to return per page. Defaults to 10, maximum 50 for search results. | |
| query | No | Natural language search terms or category keywords to find matching content pockets. Optional when creator_email or isrc is provided. | |
| content_type | No | Optional filter to show only pockets in a specific content category or source type, such as 'youtube', 'webpage', 'video', 'text', 'image', or 'audio'. | |
| creator_email | No | Optional filter to show only pockets created by the creator with this email address. Case-insensitive exact match on the email. Requires an API key; refused for anonymous callers. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so: it discloses anonymous vs. authenticated behavior (content_url and creator_id omitted anonymously), the api_key_required refusal for creator_email, the closed-catalog pull restriction, listing-row field limits, and the unlisted-pocket isrc exception. This is exactly the behavioral context an agent needs beyond structured fields.
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?
Purpose and the pull_content exclusion are front-loaded, but everything is delivered as one dense run-on paragraph with repeated schema facts (isrc exactness, creator_email API-key requirement) and return-field enumeration. It is informative yet not efficiently partitioned or scannable.
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?
Though there is no output schema, the description fully describes the result shape (IDs, titles, creators, content types, pricing tiers, catalog_id, access, delivery, and which rows omit content_url) and the paging control. Nothing an agent needs to call or interpret the tool is missing.
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 real meaning: the at-least-one-of constraint (not expressible via the empty required list), the literal-keyword matching semantics of query, and the auth caveat on creator_email. Some overlap with the schema's own isrc/creator_email text is the only detractor.
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 (search the Pockets catalog) and names the search dimensions (keyword, creator email, category). It clearly separates itself from pull_content ('Does NOT retrieve content'), but never mentions the sibling list_pockets, so an agent can't fully disambiguate between discover-via-search and list-all without inspecting both schemas.
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?
Gives explicit when-to-use ('discover available licensed content before pulling it'; 'knows the topic or creator but not the pocket ID') and a hard when-not ('use pull_content with the returned pocket_id'). The only gap is that it doesn't contrast with the list_pockets sibling.
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.
list_pockets1 field changedInput schema / properties / creator_id / descriptionPrevious value: -"Optional filter to show only pockets from a specific creator. Use the creator's unique identifier."New value: +"Optional filter to show only pockets from a specific creator. Use the creator's unique identifier. Requires an API key; refused for anonymous callers."search_pockets3 fields changedInput schema / properties / creator_email / descriptionPrevious value: -"Optional filter to show only pockets created by the creator with this email address. Case-insensitive exact match on the email."New value: +"Optional filter to show only pockets created by the creator with this email address. Case-insensitive exact match on the email. Requires an API key; refused for anonymous callers."Input schema / properties / isrcAdded value: +{
+ "description": "Optional exact ISRC lookup: the full 12-character code, dashes allowed (e.g. 'USRC17607839' or 'US-RC1-76-07839'). Matches case- and dash-insensitively; a partial ISRC is rejected. This is the only search that also returns unlisted pockets.",
+ "type": "string"
+}Input schema / properties / query / descriptionPrevious value: -"Natural language search terms or category keywords to find matching content pockets. Optional when creator_email is provided."New value: +"Natural language search terms or category keywords to find matching content pockets. Optional when creator_email or isrc is provided."list_pocketspull_contentsearch_pockets
Add one secure layer between your agents and this server.