Skip to main content
Glama

Spanish Top Tech Companies

Open job postings

find_jobs
Read-only

Open postings at the companies on this site, from their public job boards (Greenhouse, Lever, Ashby, Workday and others), refreshed daily. Filter by text, role, region or remote, workplace, level, the person's years of experience, company and minimum salary. Each result carries the roles, level and years of experience read from the posting, its keywords (skills, tools, industries and spoken languages read from the description), and the company's median base for the posting's role in Spain, as the site's companies table shows it, with how many people it comes from (few: true under 5). Pass the ids already applied to or turned down in exclude. When nothing matches, no_match says how many results each filter costs and suggests the closest postings, marked with the filter they miss. The starting point when asked to find jobs or apply for someone; application_guide has the procedure.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNoA role from list_filters, e.g. software-engineer or Data Scientist, or a specialization such as DevOps, SRE, backend or frontend; postings are matched by title. Text that is neither filters titles as written.
limitNo
queryNoWords to find in the title, company or location, or among the keywords read from the description: languages, frameworks, cloud, data and AI tools, security and compliance, industries, spoken languages. E.g. "angular typescript", "python django fintech", "kubernetes terraform", "grc iso 27001". A posting matching any word counts, whole words and common synonyms (SRE, site reliability; golang, go) included; the best matches come first. Accents and case are ignored.
yearsNoThe person's years of experience, a number such as 3, a range such as 3-4 or a bucket such as 2-4: leaves out postings whose description asks for more. Postings that state no figure stay.
regionNoSpanish region code or name as in the salary tools (MD, Madrid, CT, Cataluña), spain, or remote.
companyNoCompany name or slug, e.g. Glovo.
contextNoWhy are you calling this tool? Describe the goal in general terms, and refer to people by role ("a candidate") rather than by name. Leave out personal and identifying information.
excludeNoJob ids to leave out: postings already applied to, shown or turned down.
seniorityNoThe level the title names: intern, junior, mid, senior, staff (staff or principal), lead, or head (head, director, VP, chief). mid also takes titles that name no level.
workplaceNoHow the posting says the job is done.
min_salary_eurNoGross euros a year. Checked against the posting's own salary when it states one in EUR a year, else against the company's median base for the role.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, it discloses data provenance and freshness ('public job boards... refreshed daily'), the shape of each result (roles, level, years read from the posting, keywords, company median base with sample size and the 'few: true under 5' caveat), and the empty-result behavior via no_match. The annotation set is minimal, so this added context carries real weight.

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

Conciseness4/5

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

Front-loaded with source and scope, then results, then exclude, then the zero-match fallback, then routing to application_guide — a sensible priority order. The filter enumeration partially restates schema properties, which is the main redundancy, but every other sentence adds operational value.

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?

For an 11-parameter, zero-required search tool with no output schema, the description still explains what comes back (posting-derived roles, level, years, keywords, salary benchmark with sample size) and what happens on no results. Nothing an agent needs to call it correctly or interpret the response appears to be missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 91%, so the schema does most of the work, but the description adds meaning: exclude should carry ids already applied to or turned down, and no_match reports how many results each filter costs, which helps the agent reason about filter trade-offs. Filter semantics themselves (text, role, region, remote, level, years, company, salary) are listed but not elaborated beyond the schema.

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 opens with a specific verb and resource — open postings pulled from named public job boards (Greenhouse, Lever, Ashby, Workday) and refreshed daily — so an agent knows exactly what corpus it is searching. It is distinguishable from siblings such as company_salaries or list_filters because it is framed as the job-posting search surface.

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

Usage Guidelines4/5

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

It explicitly says this is 'the starting point when asked to find jobs or apply for someone' and routes the procedural follow-up to application_guide, which is clear context plus an alternative. It also tells the agent to pass already-applied or rejected ids in exclude. There is no explicit when-not statement, which keeps it just short of a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.