searchSearch sentences. Use ISO 639-3 codes ("eng","fra","spa","jpn","cmn",…) for from/to.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | Target translation language (default any). | |
| from | No | Source language (default any). | |
| page | No | 1-based (default 1). | |
| limit | No | 1-100 (default 25). | |
| query | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| paging | No | Pagination metadata from API | |
| results | No | Search result sentences, limited to requested count |
Changes observed during successful MCP inspections.
Input schema / examplesAdded value: +[
+ {
+ "query": "hello"
+ },
+ {
+ "from": "fra",
+ "limit": 10,
+ "query": "bonjour",
+ "to": "eng"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "paging": {
+ "description": "Pagination metadata from API",
+ "type": "object"
+ },
+ "results": {
+ "description": "Search result sentences, limited to requested count",
+ "items": {},
+ "type": "array"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, so the description does not need to repeat those. It adds the language code format instruction, which is a useful parameter-level disclosure, but no further behavioral traits (e.g., result ordering, pagination defaults) are mentioned.
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 two short sentences and wastes no words. It immediately names the action and provides the essential parameter convention.
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 the presence of an output schema and extensive annotations, the description covers basic parameters but leaves unclear the exact semantics of the search (e.g., does it return translations?) and when to use it. This is acceptable for a simple tool but could be more complete.
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 schema covers 80% of properties, but the description adds crucial format information for 'from' and 'to' by specifying ISO 639-3 codes. It does not explain 'query', which lacks a schema description, so there is a small gap.
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 'Search sentences' which gives a verb and resource, but does not clarify the domain, the nature of the search, or how it differs from siblings like 'search_within' or 'sentence'. The ISO 639-3 hint hints at translation, but the overall purpose remains ambiguous.
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 only usage guidance is 'Use ISO 639-3 codes for from/to', which is a parameter formatting instruction. No context is given for when to choose this tool over alternatives like 'search_within' or 'translations'.
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.