Instacart search-term autosuggestions for a keyword across every retailer serving a postal code at once, credential-free (unlike instacart_search's single-store lookup).
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | ||
| postal_code | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | The tool result payload (shape varies per tool; see each tool's docs resource). |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds genuinely new context by stating the call is 'credential-free', which tells the agent no auth is required. It does not cover rate limits or result volume, but against the existing annotations this is solid added value.
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?
A single front-loaded sentence with no filler; the scope and the sibling contrast are packed in efficiently. It is appropriately sized for a 2-parameter tool, though the parenthetical sibling comparison slightly crowds the sentence.
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?
An output schema exists, so return values need not be explained. For a 2-param, read-only, open-world lookup the description covers purpose, scope, auth, and the alternative route, leaving only minor gaps such as param formatting and result cardinality.
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 coverage is 0%, so the description carries the burden. It implicitly maps both params ('a keyword' -> q, 'a postal code' -> postal_code), which is better than nothing, but gives no format guidance (e.g., postal-code format, whether q supports partial terms) beyond restating the obvious.
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 states a specific resource (Instacart search-term autosuggestions) and scope (across every retailer serving a postal code), and explicitly names the sibling it differs from (instacart_search's single-store lookup). The only friction is that the tool name 'search_nearby' suggests search results while the description clarifies the output is autosuggestions, but the text resolves that ambiguity rather than creating it.
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 gives a clear selection cue: use this for cross-retailer, postal-code-wide autosuggestions 'unlike instacart_search's single-store lookup', which tells the agent when to prefer this over the sibling. It stops short of an explicit when-not rule or mention of the other instacart siblings (stores, item, departments).
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.
