Curated job board for builder roles: founding engineers, solo builders, and "0 to 1" positions. Search and filter by location, salary, seniority, workplace model, visa sponsorship, and more. No API key needed.
Scored across 3 tools
Each tool has a clearly distinct purpose: search_jobs finds jobs, get_job retrieves full details for a specific ID, and list_filters provides valid filter values. There is no overlap or ambiguity between them.
All tool names follow the same verb_noun pattern: search_jobs, get_job, list_filters. The style is consistent and predictable.
Three tools is minimal but perfectly scoped for a read-only job board: discover filters, search, view details. Each tool earns its place with no redundancy or unnecessary extras.
The server covers the complete browsing workflow for builder jobs: list_filters enables informed searching, search_jobs finds relevant listings, and get_job provides full details. No create/update/delete operations are needed for this read-only domain.
Get full details of a specific builder job by its ID, including description, skills, experience requirements, benefits, and company info. Use this after search_jobs to retrieve the complete listing.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The job ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint: true, so the tool's safe read nature is known. The description adds the specific content of the returned details (skills, benefits, etc.), which is useful but not deep behavioral context. No mention of errors, auth, or other nuances, but the annotation reduces the burden.
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 with no fluff. The first sentence states the purpose and content, the second gives usage guidance. Every word earns its place; it is concise and well-structured.
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?
For a simple one-parameter tool with a read-only annotation and no output schema, the description is complete. It tells the agent what the tool does, what fields are returned, and when to use it. No additional context is needed.
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 already covers the only parameter 'id' with a description ('The job ID'), yielding 100% coverage. The description adds no extra meaning beyond repeating 'by its ID' and doesn't clarify the ID's origin or format, so it stays at the baseline.
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 clearly states the tool's purpose with a specific verb ('Get'), resource ('builder job'), and scope ('by its ID'). It also enumerates the details returned (description, skills, experience requirements, benefits, company info), and the phrase 'Use this after search_jobs' distinguishes it from the search sibling.
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 description explicitly says when to use the tool ('Use this after search_jobs to retrieve the complete listing'), providing clear context relative to one sibling. However, it does not mention alternatives or exclusions (e.g., when not to use it or compare to list_filters), so it falls short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get available filter values for search_jobs: job types, workplace types, cities, countries, seniority levels, and companies. Call this first to discover valid filter values before searching, especially for country codes and available cities.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds usage context (e.g., 'especially for country codes and available cities') but does not disclose return format, pagination, or other behavioral details. It adds some value beyond annotations but not rich depth.
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 sentences, front-loaded with the main action and the value list, followed by clear usage guidance. No wasted 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?
For a zero-parameter discovery tool, the description is complete: it explains what the tool returns, enumerates the categories, and specifies when to use it relative to search_jobs. Given the simple schema and annotations, this suffices.
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?
There are zero parameters, so schema coverage is trivially 100%. The baseline for zero params is 4, and the description correctly avoids inventing parameter details while noting the types of values returned.
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 action ('Get available filter values') and explicitly lists the resource categories ('job types, workplace types, cities, countries, seniority levels, and companies'), clearly distinguishing it from siblings search_jobs and get_job.
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 provides explicit 'when to use' guidance: 'Call this first to discover valid filter values before searching', indicating it precedes search_jobs. It does not explicitly name when not to use or alternatives, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search and filter builder job listings on jobsbase.io — a curated board exclusively for "builder" roles (cross-functional positions where one person owns engineering, product, and delivery end-to-end: founding engineers, solo builders, 0-to-1 roles). Every job here is already an AI-native builder role, so do NOT search for generic terms like "builder", "AI", "full-stack", or "engineer" — they are redundant and will hurt results. Just use filters (country, workplace, seniority, etc.) to narrow down. Use q only for specific technologies, companies, or domain keywords. All parameters are optional.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Optional keyword for specific technologies, domains, or companies (e.g. "React", "fintech", "Stripe"). Do NOT use generic terms like "builder", "AI", "engineer", or "developer" — every job on this board already matches those. Omit to browse all jobs. | |
| city | No | Filter by city. Comma-separated for multiple: London,Berlin | |
| sort | No | Sort order: relevance (best match first), posted_at (newest first, default), salary (highest salary first) | |
| type | No | Filter by job type. Comma-separated for multiple: full-time,contract. Values: full-time, part-time, contract, freelance, internship | |
| limit | Yes | Results per page (default 30, max 100) | |
| state | No | Filter by state/province name. Comma-separated for multiple: California,Texas | |
| cursor | No | Cursor for next page of results | |
| region | No | Filter by geographic region. Comma-separated for multiple. Values: north_america, latin_america, europe, asia_pacific, middle_east_africa | |
| company | No | Filter by exact company name | |
| country | No | Filter by country code. Comma-separated for multiple: US,GB,CA | |
| workplace | No | Filter by workplace. Comma-separated for multiple: remote,hybrid. Values: remote, hybrid, on-site | |
| posted_within | No | Filter by posting date: past 24h, 3d, 7d, 14d, or 30d | |
| salary_at_most | Yes | Show jobs that can pay at most this amount annually (normalized to annual equivalent) | |
| education_level | No | Filter by minimum education level | |
| salary_at_least | Yes | Show jobs that can pay at least this amount annually (normalized to annual equivalent) | |
| seniority_level | No | Filter by seniority. Comma-separated for multiple: mid,senior. Values: internship, entry, mid, senior, lead, executive | |
| visa_sponsorship | Yes | Set to true to only show jobs that offer visa sponsorship | |
| experience_no_more_than | Yes | Show jobs requiring no more than this many years of experience |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses a non-obvious behavioral trait: generic terms like 'builder' or 'AI' are redundant and 'will hurt results.' This adds valuable context about how the search engine processes queries. However, it doesn't mention pagination or result ordering behavior, so it doesn't fully maximize transparency.
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 dense but well-organized: it front-loads the purpose, then delivers a critical usage warning, then explains filter usage. Every sentence serves a clear purpose, though it could be slightly trimmed without losing value.
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?
For an 18-parameter search tool with no output schema, the description gives strong domain context but omits pagination behavior (cursor parameter) and does not explain result structure or defaults beyond what the schema already covers. The 'all parameters optional' contradiction further undermines completeness.
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?
While schema coverage is 100%, the description makes a blanket claim that 'All parameters are optional,' directly contradicting the input schema's five required parameters. This false statement misleads agents about required inputs. The guidance about q is helpful but does not compensate for this significant inaccuracy.
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 opens with 'Search and filter builder job listings on jobsbase.io' — a specific verb, resource, and scope. It clearly distinguishes this tool from siblings (get_job, list_filters) by emphasizing the search/filter capability and the unique 'builder roles' niche.
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?
Provides explicit when-to-use guidance: 'do NOT search for generic terms' and 'Use q only for specific technologies, companies, or domain keywords.' It also directs users to 'Just use filters' to narrow down, but it doesn't explicitly mention when to prefer get_job or list_filters, limiting the alternative differentiation.
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.
search_jobs1 field changedInput schema / requiredAdded value: +[
+ "salary_at_least",
+ "salary_at_most",
+ "experience_no_more_than",
+ "visa_sponsorship",
+ "limit"
+]get_joblist_filterssearch_jobs
