merchant_auditAudit listings, semantic rank, competitor prices, payment reliability, buyer reach, and observed Base USDC activity, then return prioritized revenue fixes.
| Name | Required | Description | Default |
|---|---|---|---|
| payTo | Yes | ||
| queries | Yes | ||
| excludePayers | No |
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?
The annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only and safe nature is covered. The description adds that the tool analyzes multiple dimensions and returns prioritized fixes, but it does not disclose behaviors such as data freshness, external calls, rate limits, or the fact that this is a paid operation beyond the title. It neither contradicts annotations nor adds substantial behavioral context.
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, front-loaded sentence that begins with the action verb and immediately names the tool's scope and output. There is no filler or repetition; every phrase contributes meaning, and the priority ordering makes the purpose clear at a glance.
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 three parameters, a payment requirement, and no output schema, the description captures the high-level purpose and deliverable but leaves key operational details unstated. An agent still needs to infer what queries should contain, how payTo is used, and what the returned prioritized fixes look like. The description is adequate for a rough understanding but not fully sufficient for confident invocation.
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 0%, so the description carries the burden of explaining parameters. It does not map 'queries' to the listed audit dimensions, nor explain 'payTo' as the merchant's Ethereum address or the role of 'excludePayers.' The description's list of audited areas hints at what queries might represent but does not compensate for the total absence of parameter-level documentation.
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 opens with a specific verb 'Audit' followed by a detailed resource list: listings, semantic rank, competitor prices, payment reliability, buyer reach, and observed Base USDC activity. It closes with a clear deliverable, 'prioritized revenue fixes.' This is a precise purpose statement and, even without naming a sibling, it differentiates from merchant_snapshot by emphasizing audit and recommendations rather than a passive snapshot.
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 when to use the tool: when a merchant wants a diagnostic across several dimensions and prioritized fixes. However, it gives no explicit guidance on when to choose this over alternatives like merchant_snapshot, payment_guard, or verify_web_evidence, and it does not mention the $0.25 USDC cost as a decision factor. Usage context is implied but not stated.
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.
Several tool pairs have heavily overlapping purposes: check_url vs verify_web_evidence vs batch_check_urls all verify public URLs, while merchant_snapshot vs merchant_audit and payment_guard vs treasury_preflight cover very similar ground. The descriptions clarify some differences, but an agent could easily select the wrong tool when names alone are ambiguous.
All names use snake_case and are readable, but there is no consistent structural pattern. Some start with verbs (check_url, verify_web_evidence), while others are noun compounds (merchant_audit, payment_guard), and batch_check_urls places the verb in the middle. The naming is understandable but not predictable across the set.
At 8 tools, the count is reasonable and within the ideal range for a focused utility server. However, a few tools are near-duplicates of others, so the set feels slightly less well-scoped than the count alone suggests.
For the apparent niche of web3 payment preflight, merchant evaluation, and URL verification, the surface covers the core workflows well. The main gap is the lack of a more granular transaction-history or payment-execution tool, but agents can likely complete their intended tasks without dead ends.