Skip to main content
Glama
cdek-shopping-mcp

cdek-shopping-mcp

by heahoh

search_autocomplete

Retrieves autocomplete suggestions for a partial search query to help users complete product searches in the cdek.shopping storefront.

Instructions

Get search-box autocomplete suggestions for a partial query.

Args:
    q: Partial search text typed by the user.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "q": "<q>"
    },
    "name": "search_autocomplete"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it discloses almost nothing. It does not say what comes back (a ranked string list? objects?), how many suggestions, whether results are personalized or language-scoped, or whether calls are rate-limited. For a tool with zero annotation coverage, that is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence plus a short Args note – no padding, and the core purpose appears first. The Args block restates the only parameter, which is mildly redundant but conventional and harmless.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is genuinely simple – one required string, no nested objects, no output schema – so the description is close to adequate. The main missing piece is any hint about the shape of the response (suggestion strings vs. objects with metadata), which matters for an autocomplete consumer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the only property is titled 'Q', so the description does add the key meaning: it is partial text typed by the user. It still omits practical constraints such as minimum characters, whether an empty string is valid, or encoding expectations, leaving the parameter only partly specified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Get search-box autocomplete suggestions for a partial query.' An agent can immediately tell this produces suggestions rather than full search results. It does not, however, distinguish itself from siblings like search_products, which an autocomplete-vs-search choice would benefit from.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the phrase 'partial query' – the agent can infer this is for type-ahead suggestions rather than full searches, but there is no explicit statement of when to prefer it over search_products or what input precision is needed. No exclusions or prerequisites are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.