Skip to main content
Glama

Job Alerts: internships and new-grad roles

Search roles

search_roles
Read-onlyIdempotent

Open intern and new-grad roles, newest posting first. Returns {data: Role[], next_cursor, total}. Pass next_cursor back as cursor for the next page. Page size is up to 20 without an API key and 100 with one. Without a Realtime key, roles first detected within the Free plan's delay (minutes in the server instructions) are left out, and employer_url and ats_job_id are null. include_evidence (Realtime) adds the posting sentences behind the sponsorship, citizenship, clearance and graduation fields.

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": "search_roles"
  }
}

Input Schema

NameRequiredDescriptionDefault
groupNoCompany group slugs from list_groups, any of them; an array or a comma-separated string. REST: group.
levelNoOmit for both. REST: level.
limitNoDefault 20.
queryNoText the role title or company name contains, matched as one phrase. REST: q.
sinceNoOnly roles posted within this window. REST: since.
trackNoAny of these tracks, as an array or a comma-separated string. "swe" covers frontend, backend and fullstack. REST: track.
cursorNonext_cursor from the previous page.
degreeNoKeep roles open to this degree program: a posting that names the degrees it accepts must include it; one naming none stays in. REST: degree.
companyNoExact company name as list_companies returns it. REST: company.
countryNoISO 3166-1 alpha-2 codes, an array or a comma-separated string. Setting it replaces the US-only default. REST: country.
us_onlyNoDefault true: roles open to US applicants. false lifts it. REST: us=0.
undergradNotrue hides roles that accept only graduate degrees. REST: undergrad=1, or degree=bachelors.
workplaceNoWorkplace types, any of them; an array or a comma-separated string. REST: workplace.
citizenshipNo"not_required" hides roles whose posting requires US citizenship or US-person status (eligibility.citizenship_required true). Roles not read yet stay in. With include_clearance=true it keeps clearance roles that state no citizenship requirement. REST: citizenship.
sponsorshipNoFor an applicant who needs visa sponsorship. "needed" hides roles whose posting says no sponsorship; roles that do not say, or are not read yet, stay in. "available" keeps only roles whose posting says it sponsors. REST: sponsorship.
posted_afterNoISO 8601 time; only roles posted at or after it.
graduation_yearNoHide roles whose graduation window excludes this year. REST: grad.
include_evidenceNo
exclude_companiesNoCompany names to leave out; an array or a comma-separated string. REST: exclude.
include_clearanceNoDefault false hides roles requiring US citizenship, US-person status or a clearance. REST: clearance=1.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / degree
      Added value: +{
      +  "description": "Keep roles open to this degree program: a posting that names the degrees it accepts must include it; one naming none stays in. REST: degree.",
      +  "enum": [
      +    "bachelors",
      +    "masters",
      +    "phd"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / undergrad / description
      Previous value: -"true hides roles that accept only graduate degrees. REST: undergrad=1."New value: +"true hides roles that accept only graduate degrees. REST: undergrad=1, or degree=bachelors."
  2. First observed

TDQS

A4.2/5.0
Behavior5/5

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

The annotations cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, yet the description adds substantial behavior beyond them: the return envelope, pagination contract, tier-dependent page caps, Free-plan detection delay causing missing roles, nulled employer_url/ats_job_id without a Realtime key, and what include_evidence adds. These are plan- and entitlement-level behaviors an agent could not infer from annotations or schema.

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?

One dense paragraph, front-loaded with the result set and sort order, then pagination, then tier caveats in order of importance. Every clause carries information an agent needs to call and interpret the tool; nothing is restated from the schema.

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 a 20-parameter, zero-required search tool with no output schema, the description supplies the missing pieces: the response shape ({data, next_cursor, total}), the pagination loop, size limits, and the conditions under which fields come back null. Parameter documentation is largely delegated to a high-coverage schema, which is appropriate here.

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 95%, so the baseline is 3. The description earns an uplift by explaining include_evidence, which the schema leaves undocumented, and by tying nulled ats_job_id/employer_url fields to key tier. It does not address the default-on us_only or default-off include_clearance filters, which remain schema-only.

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

Purpose4/5

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

The description opens with a specific verb, resource and scope: 'Open intern and new-grad roles, newest posting first,' which tells an agent exactly what set is returned and in what order. It never explicitly contrasts itself with siblings like get_role (single role) or recent_changes, so differentiation is left implicit.

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

Usage Guidelines3/5

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

It gives concrete operational guidance for pagination ('Pass next_cursor back as cursor for the next page') and cap behavior (20 unkeyed / 100 with a key), which is genuinely useful. It stops short of stating when to prefer this over recent_changes or get_role, or what to do when a search returns nothing.

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.