random_wordReturn a single random word from Wordnik; filter by part of speech, min/max length, and minimum corpus or dictionary occurrence count.
| Name | Required | Description | Default |
|---|---|---|---|
| maxLength | No | ||
| minLength | No | ||
| minCorpusCount | No | ||
| hasDictionaryDef | No | ||
| minDictionaryCount | No | ||
| excludePartOfSpeech | No | ||
| includePartOfSpeech | No |
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Word ID | |
| word | No | Random word |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "hasDictionaryDef": true,
+ "maxLength": 10,
+ "minLength": 5
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "id": {
+ "description": "Word ID",
+ "type": "number"
+ },
+ "word": {
+ "description": "Random word",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. Description adds source (Wordnik) and filter options but does not disclose additional behavioral traits like rate limits, error handling, or return format. Acceptable given annotation coverage.
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?
Single sentence with clear structure. Front-loaded with verb and resource, then filters. No redundant or 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?
Description is brief but covers core purpose and filters. However, it does not explain return values (output schema exists but not described), behavior when no word matches filters, or usage of optional params. Adequate for simple tool but lacks depth for 7 param tool.
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 0%, so description must compensate. It mentions 'part of speech' (which maps to two params) and length/corpus count but omits hasDictionaryDef, minDictionaryCount, and full detail on part-of-speech params. Partial coverage leaves some parameters unexplained.
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?
Description clearly states 'Return a single random word from Wordnik' (verb+resource+source) and lists filtering capabilities. It distinguishes from sibling tools like 'random_words' (plural) and 'word_of_the_day' by specifying 'single' random word.
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?
Description implies usage for obtaining a random word with filters but does not explicitly state when to use vs alternatives like 'random_words' or other word-related tools. No exclusions or when-not guidance provided.
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.
Most tools have clearly distinct purposes, especially between Wordnik and Pipeworx domains. However, some overlap exists among data query tools (e.g., ask_pipeworx vs deep_research) and company lookups (entity_profile vs compare_entities), but descriptions are detailed enough to differentiate them in most cases.
Naming conventions are mixed: some tools use snake_case (ai_visibility_check), others use descriptive phrases (ask_pipeworx_grounded), and some are single words (remember, recall). There is no uniform verb_noun pattern, though groups like polymarket_* and scan_* provide some consistency within their subsets.
With 42 tools, the server is overloaded. It combines two distinct services (Wordnik dictionary and Pipeworx data) into one set, making it feel like two servers merged. Many tools are niche (e.g., hyphenation, random_words), increasing count without clear benefit. A split would improve coherence.
The Wordnik coverage is thorough (definitions, examples, pronunciation, frequency, etc.), and Pipeworx covers a wide range of data sources with tools for basic lookups, comparisons, research, and subscriptions. Minor gaps exist (e.g., no update/delete for Wordnik data), but overall the surface is comprehensive for the intended use.