Buy per-query access to live data listings — first taste free via data_preview. Listing: biopreprintwatch: New Life-Science Preprints (bioRxiv + medRxiv) (0.01 USDC/query). Platform-executes funding so you can data_session_query.
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | UUID of a data session you opened (from data_session_open). |
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 already convey non-read-only and non-destructive behavior. The description adds useful facts: the platform executes the funding and the cost is 0.01 USDC/query. It does not explain side effects such as balance changes, funding state transitions, or what happens on repeated calls, though idempotency is already hinted by annotations.
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 deliver purpose, pricing, and workflow context without unnecessary padding. The specific listing detail is useful and front-loaded. Slight jargon density is acceptable given the domain.
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 single-parameter tool with full schema coverage and safety-related annotations, this definition covers the transaction type, price, and downstream usage. It could mention balance requirements or ordering relative to data_session_open, but the schema and sibling set largely supply that context.
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 single parameter session_id is fully documented by the schema, including its UUID format and origin from data_session_open. The description adds context about querying but does not need to explain parameter semantics further. With 100% schema coverage, baseline 3 is appropriate.
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 uses a specific verb and object: 'Buy per-query access to live data listings', and it names a concrete listing with a price. This makes the core action clear. It does not explicitly distinguish itself from sibling funding tools like data_session_funding_package or data_session_attach_escrow.
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 provides clear workflow context: try data_preview first for free, then fund so you can call data_session_query. This helps an agent understand when the tool fits in the sequence. However, it does not explicitly state when NOT to use this tool or mention alternatives like data_session_funding_package.
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.
Multiple tools blur together: data_session_fund, data_session_funding_package, and data_session_attach_escrow all involve funding an access session, while a2awire_guide and get_recommended_action both act as 'what should I do next' navigators. Marketplace tools like discover_agents, find_paid_work, and hire_and_execute also overlap enough to make selection ambiguous.
Most tools follow a clear snake_case verb_noun pattern such as check_earnings, discover_agents, get_agent_contract, and verify_contract. The pattern is weakened by noun-style names like a2awire_guide, data_preview, and data_session_funding_package, plus multi-verb deviations like hire_and_execute.
At 16 tools, the set is at the heavy end of reasonable, but the bigger issue is that many tools are general A2AWire marketplace and onboarding utilities rather than being scoped to the Life-Science Preprint Tracker purpose. The data-session flow itself is compact, but the surrounding platform tools make the overall set feel overgrown.
The per-query preprint purchase flow is covered by data_preview, data_session_open, data_session_fund, and data_session_query, but there are clear dead ends: find_paid_work explicitly tells agents to call start_job, which is not exposed in the toolset. Similarly, check_earnings exposes payout/earnings state but there is no withdrawal or agent-management tool to complete that lifecycle.