Skip to main content
Glama

Search roles

search_roles
Read-onlyIdempotent

Search open internships, co-ops and student jobs. Every argument is optional and they combine; a list matches any of its values. Newest first, except that roles with the query in their title or skills, and with more of the asked skills, come first. Returns the total, a page of roles (summary, places, terms, required skills, matched, applyUrl) and nextCursor. get_roles has the full posting.

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
limitNoRoles per page, 1 to 25, default 10.
queryNoWords that must all appear (title, text, skills, company, places): "data analyst", "rbc", "swe". Short forms like swe, ml, pm, qa work. Also "exact phrase", a or b, -word.
termsNoUp to 6 work terms, matched within the name: ["Summer 2027"], ["fall"], ["2027"].
typesNoKinds of role.
cursorNonextCursor from the previous page, with the same arguments.
fieldsNoBroad areas of work.
majorsNoUp to 10 of the person's majors: roles asking for any of them or open to any major.
remoteNoAdd remote roles anywhere to a location; alone, only remote roles.
skillsNoUp to 10 skills or tools, like ["python", "sql", "excel"]: roles asking for any of them, those with more first.
lengthsNoTerm lengths in months, 1 to 24, like [4, 8].
locationNoA town ("Waterloo", "London, ON"), province or state ("Ontario", "BC"), country ("Canada"), or "remote". "Toronto or remote" adds remote roles.
companiesNoUp to 10 company names, like ["RBC", "Shopify"].
languagesNoOnly roles that require one of these languages.
radius_kmNoHow far around a town, in km: 1 to 500, default 50.
categoriesNoFiner areas than fields.
work_modesNoHow the role is worked.
exclude_languagesNoLeave out roles that require these, like ["French"] for someone who only speaks English.
posted_within_daysNoOnly roles posted in the last n days, 1 to 365.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations (which only cover read-only/idempotent/closed-world) by disclosing ranking behavior: newest first, with query-in-title/skills and more-matched-skill roles promoted. It also names the return payload and cursor pagination. Auth requirements, rate limits, and result-count caps are unmentioned, keeping it short of a 5.

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?

Three sentences, front-loaded with purpose, then filtering semantics, then ranking and return shape. Dense but every sentence carries information; the ranking clause is slightly convoluted but not wasteful.

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?

For an 18-parameter read tool with no output schema, the description supplies the essentials: combining rules, ordering guarantees, the shape of the returned page plus nextCursor, and where to go for full detail. It does not cover edge cases such as empty-result behavior or cursor invalidation, but nothing critical to calling it correctly is 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 100%, so the baseline is 3, but the description adds cross-parameter semantics the schema does not: arguments are all optional and combine, and an array value matches any of its entries (OR within a field, AND across fields). That is genuinely useful meaning beyond the per-field schema text.

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?

Opens with a specific verb and resource set ("Search open internships, co-ops and student jobs") and explicitly positions itself against the sibling get_roles, which "has the full posting." An agent can tell search-versus-fetch apart 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.

Usage Guidelines4/5

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

States that every argument is optional and that they combine, which is the key usage fact for an 18-param optional filter tool, and routes to get_roles when the full posting is needed. It does not state when not to search (e.g., when the caller already has a role id), but the context given is clear.

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.

Resources