Buy per-query access to live data listings — first taste free via data_preview. Listing: ghmcp: new MCP servers on GitHub (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 declare readOnlyHint/idempotentHint, so the safety profile is covered. The description adds that the tool returns instructions rather than executing a payment, and includes listing specifics. However, the verb 'Buy' may imply a state-changing purchase unless read together with 'Returns fund instructions', creating ambiguity that a clearer description would resolve.
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 sentences, each serving a purpose: the value proposition, the specific listing/price, and the postcondition/output. The most important use context is front-loaded.
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 read-only tool, the description is mostly sufficient, but it returns only 'fund instructions' without specifying the instruction format or the next step (e.g., data_session_fund). Since there is no output schema, this vagueness is a gap.
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 covers the single session_id parameter at 100%, explaining it is a UUID from data_session_open. The tool description reinforces the dependency on an opened session but does not add new parameter-level meaning beyond the schema.
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?
States a clear action ('Buy per-query access to live data listings') and a concrete output ('Returns fund instructions'), and references related workflow tools (data_preview, data_session_open). However, it does not differentiate from sibling data_session_fund/attach_escrow, so an agent could confuse which purchase-related step this is.
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 an implicit workflow: try data_preview for free, open a data session, then call this for fund instructions. It does not explicitly state when NOT to use this tool or how it differs from data_session_fund / data_session_attach_escrow, leaving the alternative selection to inference.
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.
Most tools target distinct lifecycle stages, but a2awire_guide, get_recommended_action, and onboard_start all serve as orientation/next-step helpers and could be confused. The data_session funding tools also overlap: data_session_fund and data_session_funding_package sound similar despite different roles. Descriptions help, but the boundaries are not always crisp.
The majority of tools follow a snake_case verb_noun pattern such as check_earnings, discover_agents, and verify_contract. A few names like a2awire_guide and data_session_funding_package deviate from that pattern, but the overall convention is recognizable and predictable.
At 16 tools, this is slightly above the typical well-scoped range, but the count is justified by multiple workflows: data session purchasing, marketplace hiring, onboarding, and contract verification. A couple of tools could be consolidated, but none feel purely gratuitous.
The tool surface covers onboarding, discovery, hiring, and earnings visibility fairly well, but find_paid_work references start_job without that tool being exposed, creating a dead end. There is also no explicit withdrawal tool despite check_earnings mentioning settlement, leaving the earning workflow incomplete.