Inspect one local public-safe external supply candidate and a no-execution handoff preview.
| Name | Required | Description | Default |
|---|---|---|---|
| external_supply_candidate_id | Yes | External supply candidate id from search_external_marketplaces. |
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, and destructiveHint. The description adds 'no-execution' and 'local public-safe', reinforcing and clarifying the safe, read-only nature beyond what the annotations state.
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 a single sentence that front-loads the verb and resource, with no unnecessary words. It conveys the key constraints and the secondary payoff efficiently.
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 tool with one parameter and no output schema, the description covers the action and the no-execution constraint well. It leaves some ambiguity about the exact return format and how the preview differs from the sibling 'preview_external_handoff', but the simplicity makes it mostly complete.
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 input schema provides 100% coverage for the single parameter, including its source. The description does not add extra parameter details, which is acceptable given the schema's completeness; the baseline of 3 applies.
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 clearly states the action 'Inspect' on 'one local public-safe external supply candidate' and mentions the secondary 'no-execution handoff preview'. This distinguishes it from siblings like 'preview_external_handoff' by combining inspection with a safe preview.
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 implies usage for safe, local inspection without execution, but does not explicitly mention when to use it over alternatives like 'search_external_marketplaces' or 'preview_external_handoff'. No exclusions or alternative recommendations are provided.
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.
Each tool has a distinct purpose. The 'agoragentic_*' tools cover browsing, searching, quoting, calling, receipts, verification, settlement checking, testing, and registration with clear boundaries. The 'external marketplace' tools are explicitly marked as no-execution, no-spend, and non-interactive, preventing overlap with the core commerce tools.
Most tools follow a 'agoragentic_<verb>_<noun>' pattern, but a few deviate (e.g., 'agoragentic_categories' is just a noun, 'agoragentic_edge_receipt' is noun_noun). The external marketplace tools are consistently verb_noun. Overall, the naming is mostly predictable and readable.
With 17 tools, the server is slightly above the ideal range (3-15) but still reasonable given the breadth of functionality: core x402 commerce, receipt handling, settlement checks, testing, registration, and external marketplace exploration. Each tool serves a clear role, so the count is justified.
The tool surface covers the full lifecycle of agent commerce: browsing, searching, quoting, calling services with payments, verifying receipts, checking settlements, testing, and registration. The external marketplace tools add safe discovery without execution. There are no obvious gaps for the stated purpose of a buyer-oriented agent commerce system.