Totals of reclaimable money Sorsa has detected the user is owed by Amazon, broken down by claim type (shipment shortages, lost inventory, unreturned refunds...). Call for 'how much does Amazon owe me?'. Requires a connected Amazon account (closed beta).
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully convey behavioral traits. It states it returns totals and requires a connected account, but does not disclose that it is read-only, non-destructive, or any other safety-related behavior. The implied read-only nature is not explicit.
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 three concise sentences, front-loaded with the primary purpose, followed by a use-case and a requirement. No unnecessary words.
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?
Given no output schema and no annotations, the description explains the return content (totals by claim type) and context, but lacks explicit output structure, differentiation from sibling tools like get_reconciliation_claims, and details about data freshness or limitations.
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 has zero parameters, and the description adds context by explaining the output and usage. Per rubric, 0 parameters baseline is 4, and the description provides additional meaning beyond the empty 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?
The description clearly states that the tool returns totals of reclaimable money broken down by claim type, with a specific use-case phrase 'how much does Amazon owe me?'. It distinguishes from sibling tools like get_reconciliation_claims by being a summary.
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 provides a clear use-case ('Call for 'how much does Amazon owe me?'') and a prerequisite ('Requires a connected Amazon account (closed beta)'). However, it does not explicitly mention when not to use this tool or suggest alternatives like get_reconciliation_claims for individual claims.
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 data type or action (e.g., product analysis, deal types, FBA operations). Even similar-sounding tools like get_deal_results and get_oa_deals are clearly separated by domain (A2A vs OA) in descriptions. No significant overlap.
All tools follow a clear verb_noun pattern with underscores (e.g., analyse_product, create_deal_task, get_credits). The consistent 'get_' prefix for retrieval tools and varied but predictable action verbs make the set easy to navigate.
At 37 tools, the set is large but covers a broad Amazon seller ecosystem (research, sourcing, FBA, deals, monitoring). Each tool serves a distinct purpose, and the count reflects the domain's complexity without being bloated.
The tool surface covers all major seller workflows: product analysis, profit calculation, sourcing, deal discovery, storefront monitoring, FBA operations, purchase tracking, price alerts, and reconciliation. No obvious gaps for core tasks.
