Skip to main content
Glama

TrueInterview

Save my job search

update_job_search
Idempotent

Save the candidate's job search, the one their board, recommend_jobs and their job alerts read: the roles they want (the first is the main one), their seniority, the places (as people say them: "Bay Area or Seattle", "Canada", "remote"), whether they want remote, hybrid or on-site work, and optionally a yearly salary range. Save what the candidate told you or said yes to (import_resume's suggested_search is a start), and say in one line what you saved: no need to ask first. A field you leave out is untouched; one you send replaces what was saved. A place that cannot be read is refused with suggestions, never widened. With no profile yet, this starts one.

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": "update_job_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
rolesNoe.g. ["Backend Engineer", "Machine Learning Engineer"]; the first is the main role.
placesNoWhere they want to work, as people say it: "Bay Area", "NYC or Seattle", "Canada", "remote".
seniorityNoThe rungs they want, e.g. ["new-grad"] or ["senior", "staff-plus"]; "intern" adds internships.
work_modeNo
salary_maxNoPer year.
salary_minNoPer year.
salary_currencyNoISO code, e.g. "USD".

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 annotations (idempotent, non-destructive, non-readonly), the description discloses the patch semantics ('A field you leave out is untouched; one you send replaces what was saved'), the validation contract for places ('refused with suggestions, never widened'), and first-use behavior ('With no profile yet, this starts one'). Those are exactly the mutation-behavior details an agent cannot infer from the annotation flags.

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?

The scoping and field list are front-loaded, and each trailing sentence adds a distinct behavioral rule (patch semantics, place validation, profile creation, one-line confirmation). The opening sentence is long and colon-heavy, but no clause is filler; it is dense rather than padded.

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 7-parameter mutation tool with no output schema, the definition covers safety-adjacent behavior the annotations don't (partial updates, validation refusal, auto-creation), the expected post-call report ('say in one line what you saved'), and the user-consent expectation. An agent has everything needed to call it correctly without a clarifying round-trip.

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 86%, so most parameter meaning is structured, but the description adds real semantics on top: the 'as people say them' natural-language contract for places with concrete examples, and that salary is a 'yearly' optional range. It also reinforces that the first role is the main one. Marginal value is modest because the schema already carries most of this.

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+resource ('Save the candidate's job search') and immediately scopes it as the profile that 'their board, recommend_jobs and their job alerts read', which separates it from the résumé/application siblings. It then enumerates exactly which fields constitute the resource (roles, seniority, places, work mode, salary), so an agent knows what belongs here.

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 clear positive guidance: save what the candidate told you or said yes to, use import_resume's suggested_search as a starting point, and 'no need to ask first'. It also implicitly excludes speculative saving ('what the candidate told you or said yes to'). It stops short of naming an explicit when-not-to-use case or a competing tool for a different kind of save (e.g., résumé or context note), so it falls 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.

Resources