Skip to main content
Glama
kula-ai

@kula-ai/mcp-server

Official
by kula-ai

search_candidates

Search for candidates by full-text query, skills, tags, sources, job pipeline, location, or resume status. Cursor-based pagination enables efficient browsing.

Instructions

Search candidates using Elasticsearch with rich filters and cursor-based pagination. Preferred over list_candidates when you need: full-text search (name, email, resume), filtering by skills, tags, sources, job pipeline, location, or resume presence. Pagination: pass cursor from the previous response meta.next_cursor to get the next page. IMPORTANT: if you change any filter or search parameter, omit cursor and start a new request — cursors are tied to a specific search context and will return wrong results if filters change.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cursorNoPagination cursor from the previous response meta.next_cursor. Omit this field entirely when changing any filter — cursors are bound to a specific search context. Cannot be combined with page.
queryNoFull-text search across name, email, phone number, and resume text
skill_idsNoComma-separated skill IDs — returns candidates who have ALL of these skills
tag_idsNoComma-separated tag IDs — returns candidates who have ANY of these tags
candidate_source_idsNoComma-separated source IDs — get IDs from list_sources
job_idsNoComma-separated job IDs — returns candidates who have applied to these jobs
has_resumeNotrue = only candidates with a resume; false = only without
country_idNoFilter by country ID
state_idNoFilter by state/province ID
city_idNoFilter by city ID
credited_to_user_idsNoComma-separated user IDs — returns candidates credited to these users
current_company_idsNoComma-separated company IDs — returns candidates currently at these companies
degree_idsNoComma-separated degree IDs — returns candidates with these degrees
institute_idsNoComma-separated institute IDs — returns candidates from these institutions
interviewer_idsNoComma-separated user IDs — returns candidates interviewed by these users
pageNoPage number (default: 1). Cannot be combined with cursor.
limitNoItems per page (default: 20, max: 100)
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses that cursors are tied to a specific search context and warns about wrong results if filters change. However, it does not explicitly state that the operation is read-only (non-destructive), which could be inferred but is not stated. Still, the description adds significant behavioral context.

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

Conciseness5/5

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

The description is concise with two well-structured paragraphs: first explaining the tool's purpose and filter capabilities, second detailing pagination with important warnings. No unnecessary sentences, and critical instructions are highlighted.

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

Completeness4/5

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

Given 17 parameters, full schema coverage, no output schema, and no annotations, the description covers key aspects: when to use, filter types, pagination mechanics, and warnings. It lacks explanation of what fields are returned in the response, which would be helpful for a search tool. Minor gap for completeness.

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 coverage is 100% with detailed parameter descriptions. The tool description does not add new parameter semantics beyond what the schema provides, but it reinforces the critical cursor behavior rule. Since schema already handles parameter explanation, a baseline 3 is appropriate.

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

Purpose5/5

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

The description clearly states it searches candidates using Elasticsearch with rich filters and cursor-based pagination. It also distinguishes from list_candidates by listing specific use cases (full-text search, filtering by skills, tags, etc.). This provides a specific verb+resource and differentiates from siblings.

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

Usage Guidelines5/5

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

Explicitly says 'Preferred over list_candidates when you need...' and lists conditions. Provides important pagination instructions: 'if you change any filter or search parameter, omit cursor and start a new request'. This gives clear when-to-use and when-not-to-use guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kula-ai/kula-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server