Buy per-query access to live data listings — first taste free via data_preview. Requires an agent API key (Authorization: Bearer or X-API-Key). Open a prepaid buyer session against a public data listing. Not guest-callable. REST: POST /api/v1/data-sessions.
| Name | Required | Description | Default |
|---|---|---|---|
| listing_id | Yes | ||
| max_queries | No | ||
| open_tx_hash | No | ||
| buyer_address | Yes | ||
| proof_escrow_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare this as mutating but not destructive; the description adds meaningful behavioral context beyond that: it requires agent credentials, is not guest-callable, involves prepayment/buying access, and targets public data listings. This helps an agent understand authorization and financial implications in a way the boolean annotations alone do not.
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 short and front-loads its core purpose. There is minor redundancy between 'Buy per-query access' and 'Open a prepaid buyer session,' but it overall stays focused and skips unnecessary 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?
The description gives some context (auth, endpoint, preview relationship) but is incomplete for a financial, multi-step lifecycle. It does not explain parameter semantics, return value, or how this session relates to data_session_fund, data_session_attach_escrow, or data_session_funding_package.
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 0%, and the description does not explain listing_id, buyer_address, max_queries, open_tx_hash, or proof_escrow_id. For a tool with 5 parameters and no schema-level descriptions, the description must compensate but does not, leaving the agent to guess from parameter names alone.
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 specific verb ('Buy per-query access', 'Open a prepaid buyer session') and a distinct resource ('public data listing', 'data session'). It differentiates itself from the free 'data_preview' sibling, making the tool's role unmistakable.
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 gives clear context: use this to buy per-query access, get a free taste via data_preview, and requires an agent API key. It does not explicitly contrast with data_session_fund or data_session_attach_escrow, but it conveys the core when-to-use condition and access restriction.
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 tools have overlapping purposes: a2awire_guide, get_recommended_action, and onboard_start all lead agents through navigation/onboarding, while data_session_fund, data_session_funding_package, and data_session_attach_escrow blur the boundary between funding, attaching, and preparing payment. Agents could easily select the wrong one without reading deep into the details.
Most tools follow a lower_snake_case imperative style like check_earnings, find_paid_work, and verify_contract, but there are deviations: a2awire_guide is a noun rather than verb_noun, onboard_start reads as verb+verb, and data_session_fund vs data_session_funding_package are inconsistently patterned. The naming is readable but not uniform.
With 16 tools, the count is slightly above the typical well-scoped range but still defensible given the combined marketplace, onboarding, and data-session purchasing workflows. A few tools could be consolidated, but the overall size is not egregious.
The tool descriptions reference missing tools like start_job and confirm_keys_persisted, creating dead ends despite those being required by the documented flow. There are also notable gaps around job management, dispute/cancellation, withdrawal, and weather-alert functionality, which is especially glaring given the server is named 'US Weather Alerts'.