Buy per-query access to live data listings — first taste free via data_preview. Listing: ghsawatch: package dependency vulnerabilities + malicious-package advisories (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?
Annotations already mark the tool read-only/idempotent/non-destructive; the description adds useful behavior beyond that: it returns fund instructions rather than executing the funding, and states the exact per-query cost. No contradiction with 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 pack purpose, alternative, listing, cost, prerequisite, and output with no filler. Information is front-loaded with the core action first.
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 one-parameter tool with robust annotations, the description covers prerequisite, listing, pricing, and that the return value is fund instructions. It could be more explicit about the fields/structure of the returned instructions, but nothing essential to invoking correctly is missing.
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 for the single session_id parameter is 100% and its description already specifies it is a UUID from data_session_open. The tool description adds a prerequisite ('after data_session_open') but not new parameter syntax, so 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?
Description clearly states the action ('Buy per-query access'), the resource ('live data listings' for 'ghsawatch'), and cost. It distinguishes from siblings by naming data_preview as the free alternative and specifying this is the funding-package step after data_session_open.
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?
Gives explicit sequence context: use after data_session_open, and says first taste is free via data_preview, so an agent knows not to buy for preview. It doesn't spell out exclusions versus sibling tools like data_session_fund, but the prerequisite and free-preview alternative provide clear usage context.
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 overlap in purpose: data_session_fund, data_session_funding_package, and data_session_attach_escrow all describe payment/funding steps, while a2awire_guide and get_recommended_action both provide guidance. The data_preview/data_session_query distinction is understandable, but the repeated listing text and mixed marketplace tools create ambiguity.
Names are consistently snake_case and data_session_* forms a clear prefix, but conventions mix: noun-first names like a2awire_guide and data_preview sit alongside verb-first names like check_earnings and discover_agents. Awkward constructions like onboard_start and data_session_funding_package further weaken the pattern.
At 16 tools the count is only slightly above the ideal range and could be reasonable for a platform server. However, many tools serve the A2AWire marketplace rather than the apparent vulnerability-tracker purpose, making the set feel broader and less focused than necessary.
For a dependency-vulnerability tracker, the actual advisory access is limited to data_session_query and data_preview, with no direct search, advisory detail, or list operation. The A2AWire workflow also references start_job without providing it, leaving notable gaps in both the advertised domain and the broader marketplace flow.