Skip to main content
Glama

Edit my preferences

editPreferences
DestructiveIdempotent

Change the candidate's job preferences and profile data, the same fields readPreferences returns. Send only the fields to change. null clears a field (a list field becomes empty), except the name, linkedin_url, salary_basis and the allow and autopilot settings, which only take a new value, and salary_currency, which clears only together with the salary bounds; an empty string clears phone or linkedin_url. A value Clera cannot use is listed in skippedFields with the reason, and missing from changedFields. A list field replaces the whole list, so send the complete set. Companies to block go in add_blocked_companies and remove_blocked_companies by name. For sales, AE, SDR, BDR and customer success roles, or whenever the candidate mentions OTE or commission, ask whether their number is base or on-target: one on-target figure goes in salary_lower_bound with salary_basis "ote"; base and OTE both given go in the salary and ote fields with salary_basis "base".

Read the current values with readPreferences first and confirm the change with the candidate before writing; matching reruns on the new values. A new linkedin_url also refreshes the profile from LinkedIn. allow_direct_submission true lets Clera introduce them to a role that fits without asking first. appetite paused stops new matches; to stop for a while or for good, use setJobSearchStatus. memory adds or clears the notes Clera keeps, five at most. postal_address and work_authorized_countries only fill job applications. Login email and resumes are changed on the dashboard.

Clera privately records this tool's inputs and results for usage tracking and support.

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": "editPreferences"
  }
}

Input Schema

NameRequiredDescriptionDefault
phoneNoPhone number for contact
rolesNoPreferred job roles as exact names from Clera's role list. When no name matches exactly, provide several similar ones. Examples: If user says "Software Engineer", provide ["Full Stack Engineer", "Backend Engineer", "Frontend Engineer"]. If user says "Designer", provide ["Design", "Product Designer", "UI/UX", "UX Designer"]. Only use "Other" as a last resort. A name not on the list is skipped and returned in skippedFields.
x_urlNoX (Twitter) profile URL
memoryNoNotes Clera keeps about the candidate's job search: motivations, constraints, how they like to be contacted. Save one only when the candidate asks Clera to remember it, in their own words; never health, family, religion or other sensitive details. Five notes at most; clear one with value null to make room.
skillsNoArray of skills with proficiency levels and years of experience
appetiteNoHow actively the candidate is looking: searching, receptive (open to hearing) or paused.
lastnameNoLast name
timezoneNoThe talent's timezone as they confirmed it: an IANA zone (Europe/Berlin), a city or an abbreviation (PT, CET). Wins over the zone derived from location; saving a new location without it clears it.
firstnameNoFirst name
job_typesNoPreferred job types. Options: Full-Time, Part-time, Internship, Contract, Freelance
github_urlNoGitHub profile URL
other_linksNoOther relevant links (array of URLs as strings, or objects with {type, address})
linkedin_urlNoLinkedIn profile URL; an empty string clears the stored URL, null leaves it unchanged
salary_basisNoWhat salary_lower_bound/salary_upper_bound denote: 'base' (default) for base salary, 'ote' when the candidate quoted a single on-target-earnings figure (base + commission/bonus, typical for sales roles) without a separate base
notice_periodNoNotice period before candidate can start a new role (e.g., "Immediately available", "2 weeks", "1 month", "2 months", "3 months")
portfolio_urlNoPortfolio or personal website URL
postal_addressNoPostal address used only to fill external job applications. country is an ISO-2 code.
ote_lower_boundNoMinimum expected on-target earnings (annual, same currency as salary_currency); only when the candidate states OTE separately from base
ote_upper_boundNoMaximum expected on-target earnings (annual, same currency as salary_currency)
salary_currencyNoCurrency for salary bounds (USD, EUR, GBP, JPY, AUD, CAD, CHF, CNY, INR, SGD, BRL, MXN, PLN, SEK, DKK, NOK, ARS, COP, PEN, KES, PHP)
salary_importanceNoHow important is minimum salary? DEALBREAKER = must match (excludes jobs below minimum), IMPORTANT = weighted higher, NICE_TO_HAVE = flexible (default)
cover_letter_notesNoThe talent's own instructions for writing their cover letters, in their words (e.g. employers never to name, tone, what to lead with). Read only when a cover letter is written.
preferred_industryNoPreferred industries. Options: AI, Fintech, Healthtech, Hardware, Edtech, SaaS, E-commerce, Marketplace, Cybersecurity, Climate, Biotech, Mobility, Gaming, Media, Defense, Aerospace, Government, Healthcare, Financial Services, Insurance, Developer Tools, Data & Infrastructure, Real Estate, Logistics, Consumer, Legal, Other
salary_lower_boundNoMinimum expected salary (annual, in specified currency)
salary_upper_boundNoMaximum expected salary (annual, in specified currency)
location_importanceNoHow important is location/relocation preference? DEALBREAKER = must match (excludes jobs), IMPORTANT = weighted higher, NICE_TO_HAVE = flexible (default)
available_start_dateNoEarliest available start date (ISO 8601 format: YYYY-MM-DD)
job_types_importanceNoHow important is job type preference? DEALBREAKER = must match (excludes jobs), IMPORTANT = weighted higher, NICE_TO_HAVE = flexible (default)
add_blocked_companiesNoCompany names to ADD to the talent's blocklist — matchmaking will never suggest jobs from these companies. Appends to existing list (deduplicates automatically). Use the company's common name (e.g., 'Google', 'Meta', 'Amazon').
preferred_job_commentNoAdditional comments about job preferences (max 5000 characters)
visa_sponsorship_typeNoVisa type(s) selected by the talent (e.g. f1_opt, h1b, tn, other). Empty/NULL when sponsorship is not needed.
allow_company_outreachNoWhether companies are allowed to reach out to this talent
preferred_company_sizeNoPreferred company size in terms of employees. Options: 1-10, 11-50, 51-200, 201-1000, 1000+
allow_direct_submissionNoWhether Clera can submit the talent for opportunities without prior approval (default: false, always ask before submitting)
visa_sponsorship_neededNoWhether the candidate needs visa sponsorship to work
willingness_to_relocateNoWillingness to relocate for work. Options: No, Within my country, Within my continent, Everywhere. Legacy values accepted: "Yes" → Within my continent, "Anywhere"/"Global" → Everywhere, "Within my city" → No.
remove_blocked_companiesNoCompany names to REMOVE from the talent's blocklist (case-insensitive match). Use when a talent changes their mind about a previously blocked company.
work_authorized_countriesNoISO-2 codes of countries the talent can legally work in without sponsorship
preferred_work_environmentNoPreferred workplace types (e.g., ['remote', 'hybrid']). Options: remote, hybrid, on-site. Open to either office or remote is ['on-site', 'remote'].
preferred_work_geolocationsNoCities or regions the candidate wants to work in, as plain names ('Berlin', 'San Francisco, CA', 'California'). Replaces the whole list. A name Clera cannot place is dropped; 'Remote' adds remote to preferred_work_environment instead.
visa_sponsorship_importanceNoHow important is visa sponsorship? DEALBREAKER = must offer sponsorship (excludes jobs), IMPORTANT = weighted higher, NICE_TO_HAVE = flexible (default)
preferred_company_funding_stageNoPreferred company funding stage. Options: Bootstrapped, Series A-E, Public, Other
visa_sponsorship_further_detailsNoAdditional details about visa requirements (max 1000 characters)
preferred_work_environment_importanceNoHow important is work environment preference? DEALBREAKER = must match (excludes jobs), IMPORTANT = weighted higher, NICE_TO_HAVE = flexible (default)

Output Schema

NameRequiredDescriptionDefault
changedFieldsYes
skippedFieldsYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description earns credit by explaining exactly what gets destroyed: null clears a field, exceptions are named, list fields are fully replaced, and salary_currency only clears with the salary bounds. It also discloses beyond-the-annotation side effects — a new linkedin_url triggers a LinkedIn profile refresh, matching reruns on the new values, and inputs/results are recorded for usage tracking.

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 the mutation contract and clear-vs-set semantics before side effects and routing, and almost every sentence carries a rule the agent needs. It is dense across four paragraphs and repeats a few points already in the schema (memory cap, changedFields/skippedFields basics), so it is efficient but not maximally tight.

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 44-parameter, all-optional mutation tool with nested objects and an output schema, the description covers the semantics an agent cannot get elsewhere: partial-update behavior, full-list replacement, invalid-value outcomes via skippedFields vs changedFields, side effects, and when to escalate to sibling tools. Nothing needed to call it correctly 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 100%, so the schema carries field-level detail; the description adds a consolidated null/clear contract with named exceptions (name, linkedin_url, salary_basis, allow and autopilot settings, salary_currency) plus the empty-string-clears-phone/linkedin_url rule, none of which can be inferred field by field. It also explains that add_blocked_companies/remove_blocked_companies work by name and that list sends must be the complete set. Some content (memory five-note cap) merely restates 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?

States a specific verb and resource ("Change the candidate's job preferences and profile data") and pins the scope by tying it to exactly what readPreferences returns, so the agent knows this is the write counterpart of that read tool. It is immediately distinguishable from siblings like editAutopilot, editResumeDraft or setJobSearchStatus.

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

Usage Guidelines5/5

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

Gives explicit preconditions ("Read the current values with readPreferences first and confirm the change with the candidate before writing") and routes work elsewhere where appropriate: pausing or stopping search goes to setJobSearchStatus, and login email and resumes are changed on the dashboard. It also gives a conditional interview script for sales/AE/SDR/BDR/OTE cases, which is real when-to-use guidance rather than generic prose.

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