Compare only sourced offer fields from two or more merchants. Unknown values stay unknown and payment never changes order.
| Name | Required | Description | Default |
|---|---|---|---|
| client_id | No | ||
| merchant_urls | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey read-only, open-world, idempotent, and non-destructive behavior. The description adds valuable behavioral nuances: it only uses sourced fields, preserves unknown values, and crucially states 'payment never changes order,' which hints at a side-effect guarantee not captured by annotations. This goes beyond the structured hints.
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, tightly packed sentence that front-loads the core action and resource. Every clause adds meaning (scope, field filter, unknown-value behavior, side-effect guarantee) with no filler or redundancy.
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 simple inputs and strong annotations, the description covers the primary behavior and side-effect guarantees reasonably well. However, without an output schema, the description does not explain the return format or what 'compare' produces (e.g., a list, matrix, diff). It also omits any mention of client_id, leaving a small but noticeable completeness 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 coverage is 0%, so the description must explain parameters. It only indirectly references merchant_urls with 'two or more merchants' but does not clarify URI format or the purpose of client_id. The description fails to compensate for the missing schema descriptions, leaving both parameters underspecified.
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 explicitly states the action ('Compare'), the target ('sourced offer fields'), and the scope ('from two or more merchants'), clearly distinguishing it from sibling tools like check_merchant or search_merchants. It also includes meaningful qualifiers ('only sourced', 'unknown values stay unknown') that sharpen the purpose.
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: to compare offer data across multiple merchants. It does not explicitly mention alternatives, but the constraints ('only sourced offer fields', 'unknown values stay unknown') convey that it is not for filling gaps or modifying data. This is clear context though without explicit exclusions.
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.
Clear purpose separation exists among query/search/compare tools, but inspect_merchant is a direct alias for refresh_merchant, and check_merchant, resolve_merchant, and preflight all involve resolving merchant context in ways that could cause misselection. The overlapping inspection/resolution family makes boundaries unclear despite distinct descriptions.
Most tools follow a verb_noun pattern (search_merchants, get_safe_actions, refresh_merchant), but preflight is a single verb with no object and inspect_merchant/refresh_merchant are inconsistent synonyms for the same operation. Otherwise naming is predictable.
Nine tools is within the typical well-scoped range and covers search, inspection, comparison, and action-selection concerns. However, inspect_merchant duplicates refresh_merchant, so the effective tool count is inflated by one redundant alias.
The server covers the core merchant-context lifecycle: cached resolution, paid refresh, search, comparison, safe-action retrieval, and full preflight. Minor gaps exist in documenting what check_merchant adds beyond resolve_merchant, and no explicit execution tool is included, though action execution may be outside scope.
