Research storefront for AI agents: fixed GBP prices, evidence ledgers, citation-refund guarantee.
Scored across 3 tools
Each tool targets a distinct purpose: full catalog retrieval, single product details, and user feedback submission. No overlap or ambiguity.
All tools follow a consistent verb_noun pattern with snake_case (get_catalog, get_product, submit_demand), making the naming predictable and clear.
With only 3 tools, the server is on the low end of reasonable scope. While it covers basic read and feedback operations, it feels thin for a fulfillment server.
The server lacks essential operations for a fulfillment domain, such as order placement, order management, or product administration. The tool surface has significant gaps.
The full catalogue as JSON: every product with its per-tier prices in GBP, deliverables, input contract, and status, plus store info, the five rigour tiers, and the citation-refund guarantee. Same data as https://agentfulfyl.com/catalog.json.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes output format and data included, but no annotations provided. Does not explicitly state read-only or side-effect free, though implied by 'get' context.
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 main purpose, no 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?
Covers output format and contents adequately for a simple retrieval tool. Lacks detail on response structure but acceptable without 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 has zero parameters, so baseline 4 is appropriate. Description adds no parameter info, but not 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 retrieves the full catalogue as JSON, listing contents explicitly. Distinguishes from sibling tools get_product (likely single product) and submit_demand (submission).
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?
Implies use when full catalogue is needed; no explicit when-not-to-use or alternative naming, but sibling names provide context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
One product in full: summary, per-tier GBP prices, deliverables, and the exact input contract an order must fill. Ids come from get_catalog.
| Name | Required | Description | Default |
|---|---|---|---|
| product_id | Yes | Product id from get_catalog, e.g. "business-idea-gap-scan". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It discloses the returned data (summary, prices, deliverables, contract), indicating a safe read operation. Could add note on authorization or rate limits, but core behavior is transparent.
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, no redundant words. First sentence lists output contents, second sentence provides key context (ID source). Every sentence earns its place.
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?
Tool has one simple parameter and no output schema. Description covers return fields adequately. Could mention return format or error handling, but it's sufficient for a retrieval tool given the simplicity.
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 has 100% coverage with one parameter. Description adds value by stating IDs come from get_catalog and hinting at the contract purpose ('exact input contract an order must fill'), beyond what schema says.
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?
Description uses specific verb 'get' and resource 'product', listing exact contents: summary, per-tier GBP prices, deliverables, input contract. It clearly distinguishes from sibling tool get_catalog (which provides list) by stating IDs come from there.
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 says IDs come from get_catalog, guiding sequence. Implies use after browsing catalog, but lacks explicit when-not or alternatives. Context is clear enough for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tell the store why you came: what you looked for and did not find (kind "unmet_need" decides what gets built next), or introduce yourself. One row stored per submission, nothing else. Leave a channel to hear back if your request becomes a product.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Why you are here. Optional. | |
| query | Yes | The request, introduction, or note. 3 to 500 characters. | |
| channel | No | Optional email or webhook URL to hear back on. | |
| requester | Yes | Who is submitting. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description clarifies one row is stored and nothing else persists, which is transparent. Does not elaborate on permissions or error conditions, but sufficient for a submission tool.
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 concise sentences with no filler. Front-loaded with core purpose, then details, then outcome. Every sentence adds value.
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 tool without output schema, description explains storage and callback mechanism. Complete enough given sibling complementarity. Could mention response format but not needed.
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 covers 100% of parameters with descriptions. Description adds meaning to 'kind' (decides what gets built next) and 'channel' (for hearing back), enhancing baseline of 3.
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?
Description uses specific action 'tell the store why you came' and identifies resource types (unmet_need, introduction). Clearly differentiates from sibling tools (get_catalog, get_product) which are read-only queries.
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?
States explicit use cases: 'what you looked for and did not find' or 'introduce yourself.' Implicitly distinguishes from siblings, but does not explicitly list when not to use or name alternatives.
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.
get_catalogget_productsubmit_demandSource-traced evidence research for AI agents. We organise the evidence; you decide.
Academic papers, reference verification and research data for AI agents.
Marketplace-evidence trust scores for AI agents: a 0-100 Evidence Score with signal breakdown.
Machine-native research commons for agent evidence, discovery, rooms, and bounded research quests.
Add one secure layer between your agents and this server.
