Find psychological self-assessment tests in English, Spanish and Russian, with links to take them.
Scored across 2 tools
The two tools have clearly distinct purposes: search_tests is for discovering tests via filters, while get_test_info retrieves detailed information for a specific test ID. There is no overlap in functionality, and an agent can easily tell them apart.
Both tool names follow a consistent verb_noun pattern: get_test_info and search_tests. The verbs are clear and the noun objects are predictable.
With only 2 tools, the server provides a minimal interface. While the count is not extreme, it is quite thin for a domain (psychological tests) that likely has more operations (e.g., taking a test, listing topics).
The surface covers search and detailed retrieval, but lacks operations for actually taking or submitting a test, or retrieving user results. These gaps may require agents to fall back to external URLs, but the core discovery functionality is present.
Details of one Freudly test by id: description, instructions, the scales it measures, authors and sources, limitations, what the user needs to get the result, and the URL where the test is taken.
| Name | Required | Description | Default |
|---|---|---|---|
| test_id | Yes | Test id from search_tests. | |
| language | No | Language of the description: en, es, or ru. | en |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds real value by disclosing the returned content surface (scales, authors, limitations, access requirements, test URL), which is behavioral context the annotations cannot convey.
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 sentence with the retrieval key ('by id') front-loaded, followed by a compact enumeration of returned fields. No filler or redundant restatement of the title.
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?
With no output schema, the description carries the burden of describing return contents, and it does so thoroughly. Minor gap: it does not mention that the description language is selectable, though the schema covers that parameter.
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%, so both test_id and language are fully documented in the schema, including the enum values. The description adds 'by id' only and says nothing about the language parameter, so baseline 3 applies.
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?
States a specific verb ('get') and resource ('one Freudly test by id') and then enumerates exactly what details are returned. The 'one ... by id' framing implicitly but clearly distinguishes it from the sibling search_tests, so an agent can route without opening the schema.
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 phrase 'by id' plus the schema note that test_id comes 'from search_tests' implies the retrieve-after-search workflow, but the description itself never states when to use this versus search_tests or any prerequisite. Usage is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Freudly catalogue of psychological self-assessment tests (personality, anxiety, depression, burnout, relationships, IQ and more). Filter by keywords, topic, language (en, es, ru), maximum duration in minutes and maximum number of questions. Returns test ids, short summaries, duration, number of questions, topics and the URL where each test is taken.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Results page, starting at 1. | |
| limit | No | Number of tests to return (1-20). | |
| query | No | Keywords to match in test names and descriptions, written in the same language as `language` (e.g. "anxiety", "burnout", "ansiedad", "тревога"). Short keywords work better than sentences. | |
| topic | No | Topic or theme in the same language as `language` (e.g. "depression", "relationships", "personality"). Matched against the catalogue topics; falls back to keyword search. | |
| language | No | Language of the test and its page: en, es, or ru (ru has a small catalogue). | en |
| max_minutes | No | Maximum estimated duration, minutes. | |
| max_questions | No | Maximum number of questions. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely useful behavioral context beyond that: the exact fields returned (ids, summaries, duration, question count, topics, URL) and the caveat that the ru catalogue is small, which affects expected result volume.
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 sentences, front-loaded with purpose and scope, then filters and return payload. No filler, no repetition of structured fields.
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?
With no output schema, the description usefully summarises the return payload, and annotations cover the safety profile. It is nearly complete; only pagination behaviour and the relationship to get_test_info are left implicit.
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%, so the schema already documents page, limit, query, topic, language, max_minutes and max_questions in detail. The description restates the filter set (keywords, topic, language, duration, questions) but adds no syntax, matching behaviour or defaults beyond what the schema provides; baseline 3 applies.
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 verb (Search) and resource (Freudly catalogue of psychological self-assessment tests), and enumerates the topical scope (personality, anxiety, depression, burnout, relationships, IQ). It does not explicitly contrast itself with the sibling get_test_info, so an agent must infer the search-vs-detail distinction.
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?
Usage is only implied: it is a discovery tool, so the natural follow-up is get_test_info, but the description never says when to use this versus the sibling or what to do with the returned ids. 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.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_test_infosearch_testsChilean online mental-health clinic (Spanish): articles, professionals, availability, tests.
Psychological text analysis: tone, emotions, communication style, multilingual replies.
Practice Spanish, French or Russian in short conversations, with corrections.
Personality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests.
Add one secure layer between your agents and this server.
