Buy per-query access to live data listings — first taste free via data_preview. Listing: New MCP Server Directory (Agent Tools Index) (0.01 USDC/query (max 20 queries/session)). Open a prepaid session, then fund and query.
| Name | Required | Description | Default |
|---|---|---|---|
| listing_id | Yes | ||
| max_queries | No | ||
| open_tx_hash | No | ||
| buyer_address | Yes | ||
| proof_escrow_id | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only indicate a non-read-only write; the description adds meaningful behavioral context: the cost per query, the max 20 queries/session, and the prepaid/payment flow. It also implies a mutating, financially relevant action without contradicting the readOnlyHint=false flag.
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 compact and front-loaded: the first clause states what the tool does, and the pricing/listing detail earn their place. Only minor ambiguity around 'Buy... access' versus the likely 'open session' action keeps it from a perfect score.
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 five parameters, no output schema, and no parameter-level documentation, the description is too thin on outcome details. An agent cannot tell what a successful open returns, which fields are required for the payment/escrow flow, or how to use the returned session. It orients the workflow but not enough for reliable invocation.
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 0%, so the description must compensate for parameter semantics. It does not explain listing_id, buyer_address, open_tx_hash, proof_escrow_id, or the relationship between max_queries and the stated per-session cap. It adds high-level context about per-query billing but leaves required and optional fields largely to inference.
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 exact action ('Open a prepaid session'), the resource ('live data listings'), and even the specific listing. It clearly separates this from the free data_preview and from later steps by saying 'then fund and query.'
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 tells the agent when to use data_preview instead ('first taste free via data_preview') and positions data_session_open as the first paid step: 'Open a prepaid session, then fund and query.' It does not explicitly enumerate all sibling alternatives, but the workflow is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several data-session tools have unclear boundaries: data_session_fund, data_session_funding_package, and data_session_attach_escrow all describe different ways of funding or attaching payment, but an agent could easily pick the wrong one. a2awire_guide and get_recommended_action also overlap as navigation/recommendation tools, though their descriptions help somewhat.
Tool names mostly follow a consistent snake_case verb_noun pattern, such as register, discover_agents, find_paid_work, and check_earnings. Minor deviations like a2awire_guide and data_preview are noun-led, but the overall convention is predictable and readable.
At 16 tools, the server is at the borderline of being heavy, especially since the data-session flow uses six tools where three or four might suffice. The count is not chaotic, but the funding-related tools feel over-decomposed for the apparent scope.
The tool set covers onboarding, discovery, hiring, earnings, and data sessions, but find_paid_work explicitly instructs agents to 'call start_job with a job_id' and no start_job tool exists in the set. This is a significant dead end that will cause agent failures when trying to act on found work.