workorai

Search matched jobs

candidate.search_jobs

Semantically rank published jobs against the authenticated candidate profile (embedding-based fit). Optional tier (best|good|weak) narrows to a match-quality band — start with tier:'best' for the strongest fits and cascade only if needed; omit for the full ranked list (read tierCounts for the band sizes). Each scored row carries matchExplanation (the white-box 'why': fit score, the candidate's skills that match the job's required set, and a rationale). A free-text q, or a candidate who has not completed an interview yet, instead browses published jobs by recency — those rows carry NO fit score (matchScore is null, no bands); treat them as a browse list, not a ranking.

Input Schema

TableJSON Schema

Name	Required	Description
`q`	No
`tier`	No	Match-quality band. Omit for the full ranked list. START with tier:"best" (strongest fits), cascade to "good"/"weak" only if you need more; read tierCounts to decide. Ignored on a free-text q / no-interview browse (no bands).
`limit`	No
`apiKey`	No	Optional WorkorAI MCP key for in-session authentication when the MCP client was initialized anonymously.
`offset`	No
`jobType`	No
`seniority`	No
`workModel`	No

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	No
`jobs`	No
`page`	No
`filters`	No
`tierCounts`	No	Band sizes for a tier cascade: matched = jobs covering >=1 required skill, unmatched = none; best/good/weak split the matched pool (all bands 0 on a free-text q / no-interview browse). Start at tier:'best', cascade if needed.

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and excels: it discloses the semantic ranking mechanism, the optional tier behavior, the fallback browse mode with null matchScore, and the content of matchExplanation. This gives the agent a clear model of what to expect.

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 dense but every sentence adds unique value: main purpose, tier usage, fallback behavior, and row composition. It is front-loaded and avoids filler, making it appropriately sized for the tool's complexity.

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

Completeness5/5

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

Given an output schema exists and the tool has 8 parameters, the description covers the two most crucial behavioral nuances: the ranked vs. browse distinction and the matchExplanation payload. It fully equips an agent for correct invocation without needing to infer hidden behavior.

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 only 25%, so the description must compensate. It does for q and tier in detail, but leaves limit, offset, jobType, seniority, and workModel undocumented—though their names and enums make them somewhat self-explanatory, the dual-mode interaction with these filters is not addressed.

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 states a specific verb ('rank') and resource ('published jobs against authenticated candidate profile') with a distinctive method ('embedding-based fit'). It clearly distinguishes from siblings like employer.search_candidates_by_query and candidate.get_job.

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 instructs to start with tier:'best' and read tierCounts, and to omit tier for full ranking. It also explains when the tool degrades to a recency-based browse (free-text q or no completed interview) and warns not to treat those rows as a ranking.

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

All workorai tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0

Disambiguation5/5

Every tool in the candidate and employer sets targets a distinct action or resource with no ambiguity. Tools like `search_candidates_by_query` and `search_candidates_for_job` have clearly different purposes, and all other tools perform unique operations.

Naming Consistency5/5

All tools follow a consistent `domain.action` pattern with snake_case action names. The naming is uniform across both candidate and employer tools, using standard verbs like get, list, create, update, delete, search, set, etc.

Tool Count4/5

29 tools cover two distinct user roles (candidate and employer) with separate workflows. While above the typical 3-15 range, each tool serves a specific purpose and the count is justified for a hiring platform's API surface.

Completeness4/5

The tool surface provides comprehensive CRUD and lifecycle operations for jobs, applications, invitations, and candidate searches for both roles. Minor gaps like candidate profile update tools are likely handled outside the MCP server, so the set feels nearly complete.

Search matched jobs

Input Schema

Output Schema

TDQS

Glama MCP Gateway

TDQS

Resources