collect_flash_auditStatus of an x402 order while it settles and generates; once DELIVERED, the report JSON itself. Poll every 10-15 seconds. Free.
| Name | Required | Description | Default |
|---|---|---|---|
| orderKey | Yes |
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 this as read-only, idempotent, and non-destructive. The description adds meaningful behavioral context: it returns status while settling, switches to the report JSON after DELIVERED, and is free. This goes beyond the annotations without contradicting them.
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 only three short phrases, each adding value: behavior during settlement, the delivered result, and polling cadence. It is front-loaded with the core purpose and contains no filler.
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 simple polling tool with one parameter, no output schema, and strong safety annotations, the description covers the key behavior and timing. It could be slightly more complete by noting that orderKey comes from buy_flash_audit, but it is not critically incomplete.
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 schema has 0% description coverage for the only parameter, orderKey. The description mentions 'an x402 order' but never explains where orderKey comes from, how it is validated, or how to obtain it, leaving the agent to infer the parameter meaning from the pattern alone.
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 tool returns the status of an x402 order and, once DELIVERED, the report JSON itself. This is a specific, actionable description that distinguishes it from siblings like buy_flash_audit and check_contract_free.
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 explicitly instructs the agent to poll every 10-15 seconds and implies use while an order is settling. It does not explicitly name alternatives or state when not to use the tool, but the polling guidance is clear and useful.
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 targets a distinct stage: getting payment terms, initiating a paid audit, collecting its result, or performing a free on-chain check. The overlap between flash_audit_terms and the unpaid response from buy_flash_audit is clearly explained, so an agent can reliably tell them apart.
buy_flash_audit and collect_flash_audit follow a clear verb_noun pattern, but check_contract_free adds a trailing adjective and flash_audit_terms drops the verb entirely. The names are readable and descriptive, yet the conventions are mixed.
Four tools exactly cover the server's narrow scope: one free check, plus the three-step paid audit workflow of terms, buy, and collect. No tool feels redundant and the count is well below any bloat threshold.
The free check is a self-contained operation, and the paid audit flow is complete from fetching terms to buying and polling for the delivered report. There are no obvious dead ends or missing lifecycle steps for the stated purpose.