If it's here, it's on their board - live jobs from employer career pages, apply on theyond.com.
Scored across 2 tools
The two tools have clearly distinct purposes: get_job retrieves a specific job by URL/slug, while search_jobs finds jobs by keyword/location/etc. The descriptions explicitly state when to use each and reinforce the boundaries (e.g., 'Do not use this to search').
Both tools follow a consistent verb_noun pattern: get_job and search_jobs. The naming is predictable and clear.
The server has only 2 tools, which is somewhat thin for a job search domain, but it covers the core actions of searching and retrieving a job. More tools (e.g., for filtering or details) could be useful, but the minimal set is reasonable for its focused purpose.
The surface covers basic search and retrieval, but lacks other common job-related operations such as listing companies, getting job details beyond the URL, or saving jobs. However, for a minimal job search interface, it may be sufficient, though notable gaps exist (e.g., no pagination, no advanced filters).
Use after search_jobs when the user picked one job. Pass that job's url from search_jobs (or its slug). Do not use this to search. Plain-text description. No employer apply URL.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | The theyond.com job URL from search_jobs. Prefer this. | |
| slug | No | Job slug from search_jobs. Use if you don't have the URL. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is already covered. The description adds behavioral context by specifying the return format ('Plain-text description') and the absence of an apply URL, which is useful for setting agent expectations. However, it does not go into depth about other behaviors like rate limits or pagination, but given the annotations, the description adds reasonable value.
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 concise, with three sentences, and front-loads the key usage context ('Use after search_jobs'). It avoids unnecessary detail and each sentence adds value. It loses a point because it could be slightly more structured by explicitly naming the sibling, but overall it is efficient.
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 tool with two optional parameters printable in the schema and an output that is a plain-text description, the description covers the essential usage context (when to use, what to pass, what to expect) sufficiently. It could mention error handling or what happens if neither parameter is provided, but given the tool's simplicity and annotation coverage, it is nearly complete.
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 describes both parameters in detail (url and slug) with clear guidance on preference. The description reinforces the preference for url over slug and emphasizes that they come from search_jobs, which adds semantic context. Since schema coverage is 100%, a baseline of 3 is appropriate, and the description provides marginal added value.
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 retrieves a single job after search_jobs, distinguishing it from the sibling search tool ('Do not use this to search'). It specifies a single resource (a job) and the context in which it is used (after search_jobs). However, it does not explicitly name the sibling in the purpose statement, though it does refer to 'search_jobs' later.
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 provides explicit usage guidance: 'Use after search_jobs when the user picked one job. Pass that job's url from search_jobs (or its slug).' It also tells the agent not to use it for searching, and clarifies the output (plain-text description, no apply URL). This is clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find live jobs when the user has a keyword, place, company, and/or remote, not a theyond job URL (use get_job for that). Need q, location, company, or remote=true. Returns at most 10 theyond.com pages, no pagination, no employer apply URLs. theyond_verified_at is when theyond last saw the listing on the employer board, not the posted date. People apply from the theyond page.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Keywords for title, company, or description. Optional if location, company, or remote is set. Do not pass a theyond.com/jobs URL here. | |
| remote | No | If true, only jobs whose title or location looks remote. Combine with q or company. | |
| company | No | Employer name, case-insensitive. nvidia matches NVIDIA. Optional if q, location, or remote is set. | |
| location | No | City, region, or country. Optional if q, company, or remote is set. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnly, openWorld, idempotent, non-destructive), and the description adds substantive behavior beyond them: a 10-page result cap, no pagination, no employer apply URLs, the meaning of theyond_verified_at versus posted date, and where users apply from.
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?
Dense and front-loaded with the routing rule first, and nearly every clause carries distinct information. The trailing sentence about applying from the theyond page is useful but slightly tangential to invocation.
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 return-value burden and does so: result cap, absence of pagination, absence of apply URLs, and the semantics of a notable field. Nothing essential for correct invocation is missing.
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 coverage is already 100%, so baseline is 3, but the description adds a cross-parameter constraint the schema does not encode: at least one of q/location/company/remote must be set. Field-level meanings themselves remain entirely in the schema.
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+resource (find live jobs) and explicitly carves out the sibling case: URLs go to get_job, not here. An agent can distinguish search_jobs from get_job without opening either 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?
Explicit when-to-use ('when the user has a keyword, place, company, and/or remote'), explicit alternative ('use get_job' for a job URL), and the minimum input condition ('Need q, location, company, or remote=true'). No inference required.
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 / properties / company / descriptionPrevious value: -"Employer name, case-insensitive. Shopify matches Shopify and Shopify Inc. Optional if q, location, or remote is set."New value: +"Employer name, case-insensitive. nvidia matches NVIDIA. Optional if q, location, or remote is set."search_jobs4 fields changedInput schema / properties / companyAdded value: +{
+ "description": "Employer name, case-insensitive. Shopify matches Shopify and Shopify Inc. Optional if q, location, or remote is set.",
+ "type": "string"
+}Input schema / properties / location / descriptionPrevious value: -"City, region, or country. Optional if q is set. Combine with q to narrow."New value: +"City, region, or country. Optional if q, company, or remote is set."Input schema / properties / q / descriptionPrevious value: -"Keywords for title, company, or description. Optional if location is set. Do not pass a theyond.com/jobs URL here."New value: +"Keywords for title, company, or description. Optional if location, company, or remote is set. Do not pass a theyond.com/jobs URL here."Input schema / properties / remoteAdded value: +{
+ "description": "If true, only jobs whose title or location looks remote. Combine with q or company.",
+ "type": "boolean"
+}get_job3 fields changedInput schema / properties / slug / descriptionPrevious value: -"Job slug or theyond.com job URL"New value: +"Job slug from search_jobs. Use if you don't have the URL."Input schema / properties / urlAdded value: +{
+ "description": "The theyond.com job URL from search_jobs. Prefer this.",
+ "type": "string"
+}Input schema / requiredRemoved value: -[
- "slug"
-]search_jobs2 fields changedInput schema / properties / location / descriptionPrevious value: -"City, region, or country"New value: +"City, region, or country. Optional if q is set. Combine with q to narrow."Input schema / properties / q / descriptionPrevious value: -"Keywords (title, company, description)"New value: +"Keywords for title, company, or description. Optional if location is set. Do not pass a theyond.com/jobs URL here."get_jobsearch_jobs
