Skip to main content
Glama

search_gojobs

Search Ontario Public Service job postings by title, location, job category, career level, or minimum salary to find government roles despite the board lacking keyword search.

Instructions

Search gojobs.gov.on.ca, the Ontario Public Service (OPS) careers board. Every posting is an Ontario government job. The board has NO keyword search of its own — its only text input is an exact Job ID — so title is matched here against each posting's own title. Region, city, job category, career level and minimum salary are real board filters. Give at least one filter — an unfiltered listing is a dozen sequential postbacks.

Input Schema

NameRequiredDescriptionDefault
limitNoJobs to return (default: 25)
titleNoJob title, e.g. "policy advisor"
locationNoOntario city or region, e.g. "Toronto", "Thunder Bay", "North". "Ontario" and "Canada" cover the whole board and are treated as no filter.
min_salaryNoMinimum annual salary the board offers as a step, e.g. "70000", "100000"
career_levelNoOne of: Student, Entry level, Experienced, Management, Executive
job_categoryNoOPS job category, e.g. "Information Technology", "Corrections and Enforcement"
strict_titleNoRequire the title words to appear in the posting's title

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.8.6

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it explains that the board has NO keyword search, that its only native text input is an exact Job ID, and that `title` is therefore matched client-side against each posting's own title. It also warns that unfiltered listings trigger "a dozen sequential postbacks," a useful performance trait. It stops short of covering return shape or pagination, hence not 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.

Conciseness5/5

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

Three sentences, zero waste, and the most decision-relevant fact (the board's lack of keyword search) is front-loaded right after the identity sentence. Every clause earns its place by either orienting the agent or preventing a costly invocation mistake.

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?

Given seven params with 100% schema coverage but no annotations and no output schema, the description supplies the key behavioral context an agent needs to call it correctly. The one remaining gap is the absence of any indication of what the results look like or how `limit` interacts with the sequential-postback warning, but for a public search tool this is a minor omission rather than a blocking one.

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 real semantic value the schema lacks: it explains that `title` is matched locally against posting titles because the board has no keyword field, and it clarifies which fields (region, city, job category, career level, minimum salary) correspond to genuine board filters. The special

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 names a specific verb and resource ("Search gojobs.gov.on.ca, the Ontario Public Service (OPS) careers board") and immediately clarifies what kind of postings it returns ("Every posting is an Ontario government job"). This source identification cleanly distinguishes it from the many other job-board search siblings without needing to name each one.

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 gives a concrete invocation requirement — "Give at least one filter — an unfiltered listing is a dozen sequential postbacks" — which maps directly to the anyOf constraint and explains the cost of ignoring it. It does not explicitly compare against siblings like get_gojobs_job or the other portal search tools, so the when-to-use alternative guidance is implied rather than stated.

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