TF-IDF search across the AMZScout knowledge base (Amazon-seller tutorials, brand reference, glossary). Returns the top-K relevant chunks with title, source URL and text. Use this to ground answers in factual material.
| Name | Required | Description | Default |
|---|---|---|---|
| topK | No | How many knowledge chunks to return (1–20) | |
| query | Yes | Search phrase. 2-300 chars. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds meaningful behavioral detail beyond that: it reveals the TF-IDF retrieval mechanism, that results are relevance-ranked chunks, and that each result includes title, source URL, and text. No contradiction with annotations.
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?
Two tightly scoped sentences with no filler. The search target and result fields are stated first, and the usage directive is a clear closing instruction. Every sentence earns its place.
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 two-parameter read-only search tool with no output schema, the description is complete: it names the resource, the search mechanism, the result contents, and the intended use. An agent has enough information to invoke it appropriately and interpret its response.
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 100%, with both 'query' and 'topK' already documented. The description adds context that 'top-K' refers to returned chunks SubstituteScore and implies the query is the search phrase, but it does not need to do much more because the schema carries the parameter meaning.
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 names a specific retrieval method (TF-IDF search), a distinct resource (AMZScout knowledge base), and the return shape (top-K chunks with title, source URL, text). This clearly distinguishes it from sibling tools that analyze products, niches, or keywords.
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 instruction 'Use this to ground answers in factual material' gives a clear context for when to invoke this tool. It does not explicitly name alternatives or provide when-not-to-use guidance, but the knowledge-base purpose is evident against the analytical siblings.
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.
