Buy per-query access to live data listings — first taste free via data_preview. Listing: fdarecall: FDA recall enforcement database (food, drug, device) (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 signal a state-changing, non-destructive, idempotent operation. The description adds useful context: platform-executes funding, per-query cost, and the free-preview path. It does not detail the mechanics of funds transfer or any prerequisites, but given the annotation coverage this is a reasonable but not rich disclosure.
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 two dense sentences with no filler. The core action is front-loaded, and the listing detail plus workflow references to data_preview and data_session_query are all relevant.
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 a fully documented schema and reasonable annotations, the description covers the action, the specific listing, the cost, and the intended post-condition (can query). The prerequisite of opening a session is not in the description text, but the schema's parameter description supplies it, so the combined context is sufficient.
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 100%; session_id is fully documented as the UUID from data_session_open. The tool description adds no session_id-specific meaning beyond the schema, so it meets the baseline without additional value.
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-resource pair: 'Buy per-query access to live data listings', and names the concrete listing (fdarecall) with its price. It references data_preview and data_session_query, but does not explicitly differentiate from closely related siblings like data_session_funding_package, so it is clear but not fully distinguishing.
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 conveys a workflow: try free via data_preview, fund this session, then use data_session_query. This gives clear context. However, it never contrasts this tool with the alternative funding-related siblings (data_session_funding_package, data_session_attach_escrow), leaving the selection among them implied rather than explicit.
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.
The tool set blends FDA recall query tools with generic A2AWire marketplace tools, making purpose boundaries unclear. Multiple tools overlap: data_session_fund, data_session_funding_package, and data_session_open all describe payment/session setup, while a2awire_guide and get_recommended_action both serve as navigational helpers.
Some tools follow a verb_noun pattern (data_session_open, data_session_query, discover_agents), but others are inconsistent or vague (a2awire_guide, check_earnings, register, verify_contract). The mix of domain-specific and platform tool naming with no coherent convention makes the surface feel disjointed.
16 tools is not inherently excessive, but most are unrelated to FDA recall alerts; they cover agent registration, onboarding, escrow, hiring, and earnings. Only a handful actually concern the stated FDA recall data domain, so the count is poorly scoped for the server's apparent purpose.
For an FDA recall alert server, the surface is severely incomplete: there is no direct recall listing, search, filtering, or detail tool, only a generic data_session_query with preview. The remaining tools are platform infrastructure, leaving the actual recall domain shallow and dependent on an opaque paid query flow.