Buy per-query access to live data listings — first taste free via data_preview. Listing: RiverWatch: USGS river levels & stream-flow gauges (0.01 USDC/query). Returns fund instructions after data_session_open.
| 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?
The annotations already declare this read-only, idempotent, and non-destructive. The description adds that it returns fund instructions and depends on an already opened session, which is useful context. The word 'Buy' is potentially misleading under readOnlyHint because it implies a financial state change, though 'returns fund instructions' partially clarifies that it is not executing payment.
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 short sentences front-load the core purpose, then add the listing, price, preview alternative, and sequencing requirement with no filler. Every clause is decision-relevant and compact.
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 no output schema, it covers the essential input and returns a vague expectation of 'fund instructions.' However, the presence of data_session_fund and data_session_attach_escrow as siblings makes the missing relationship/next-step guidance a real gap for correct usage.
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%: session_id is already described as the UUID from data_session_open, so the schema fully documents the only parameter. The description reinforces the data_session_open dependency but adds no new parameter-level detail, matching the baseline 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?
The description names a concrete action ('Buy per-query access'), the specific listing (RiverWatch at 0.01 USDC/query), and the required prerequisite (data_session_open), so an agent understands what the tool does. It does not fully distinguish this from sibling funding tools like data_session_fund or data_session_attach_escrow, so it stops short of a 5.
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?
It provides useful sequencing by saying to call it after data_session_open and points to data_preview for a free trial. However, it never explicitly contrasts this tool with data_session_fund or data_session_attach_escrow, nor does it explain when not to use it or what the follow-up funding step is.
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 occupy overlapping roles: data_session_fund, data_session_funding_package, and data_session_attach_escrow all describe funding or payment for a data session, while a2awire_guide, get_recommended_action, and onboard_start all point toward 'what to do next.' An agent could easily misroute payment or onboarding intent.
Most names follow a snake_case verb_noun pattern like data_session_open, find_paid_work, and verify_contract. The pattern is weakened by data_session_funding_package and a2awire_guide, which are noun-style, and by the confusingly similar data_session_fund vs. data_session_funding_package.
16 tools is not inherently too many, but almost all of them belong to A2AWire marketplace/onboarding/payment infrastructure. Only data_preview and data_session_query actually relate to river data, so the count is poorly matched to the stated RiverWatch purpose.
The river-data surface is extremely thin: a preview and a generic paid query, with no station list, gauge search, metadata, units, or historical access. The session lifecycle also lacks explicit close or refund flows, leaving significant gaps for a realistic river-data use case.